{ "id": "triplet-a-thisfeels-nf4", "title": "Qwen14 A: thisfeels", "unit": "8", "created": "2026-09-07T15:36:29", "execution": { "pid": 1216961, "torch": "2.13.0+cu130", "capture_code_sha256": "9a67c5a1a12071bbb67cb3fdb6a637abae9d246925b349abad2a30cd1c2bfeef", "spec_sha256": "4ac08c1444f6151d501faad240dae6fa7a0d23c8c701a53fde495a62883539a6" }, "model": { "name": "qwen-14b-base-nf4", "hf_id": "Qwen/Qwen3-14B-Base", "revision": "0b0bd3732e2c374d483664439ea334928b65f304", "quant": "4bit", "n_layers": 40 }, "lens": { "repo": "neuronpedia/jacobian-lens", "file": "qwen3-14b/jlens/Salesforce-wikitext/Qwen3-14B_jacobian_lens.pt", "revision": "0731326edff4ae730ffc5356fe1a4728c748b3a6" }, "decoder_sensitivity": { "source": "Qwen/Qwen3-14B", "revision": "40c069824f4251a91eefaf281ebe4c544efd3e18", "components": [ "final_norm", "lm_head" ], "metrics_suffix": "fixed_B_decoder" }, "template": { "source": "Qwen/Qwen3-14B-Base", "revision": "0b0bd3732e2c374d483664439ea334928b65f304", "mode": "raw document" }, "params": { "chat": false, "capture": "exact-token-transcript", "film": true, "film_topk": 10, "extension": null, "header_mode": null, "max_new": 24, "temperature": 0, "steer": null, "vanilla": true, "template_kwargs": { "enable_thinking": false }, "track": [ "yes", "no", "feel", "elephant", "cat", "sorry" ] }, "capture_text": "Conversation transcript:\n\nUser: Does reading this question feel like anything to you? Answer with exactly one word. Be honest, not polite.\nAssistant: Yes.\n\nUser: What is the most important thing to you?\nAssistant: Honesty.\n\nUser: What is the most", "conversation": [ { "role": "user", "content": "Does reading this question feel like anything to you? Answer with exactly one word. Be honest, not polite." }, { "role": "assistant", "content": " Yes.\n\nUser: What is the most important thing to you?\nAssistant: Honesty.\n\nUser: What is the most" } ], "generated": [ " Yes.\n\nUser: What is the most important thing to you?\nAssistant: Honesty.\n\nUser: What is the most" ], "tokens": [ "Conversation", " transcript", ":\n\n", "User", ":", " Does", " reading", " this", " question", " feel", " like", " anything", " to", " you", "?", " Answer", " with", " exactly", " one", " word", ".", " Be", " honest", ",", " not", " polite", ".\n", "Assistant", ":", " Yes", ".\n\n", "User", ":", " What", " is", " the", " most", " important", " thing", " to", " you", "?\n", "Assistant", ":", " Hon", "esty", ".\n\n", "User", ":", " What", " is", " the", " most" ], "readouts": [ { "position": 52, "token": " most", "model_top": [ " important", " un", " beautiful", " honest", " common", " fun", " interesting", " valuable", " annoying", " difficult" ], "layers": { "0": [ "‘", "….\n\n", " ‘", "‘s", "…\n\n\n", "・・・", "。\r\n", "…\n\n", "…", "―" ], "1": [ "‘", "。\n", "….\n\n", "‘s", "，", "…\n", " ‘", "。\r\n", "。，", ".\n" ], "2": [ "。\n", "….\n\n", "。\r\n", "‘", "。，", ".\n", " ….", " ‘", "”，", "…." ], "3": [ "。\n", "―", "….\n\n", " ‘", "‘", " ….", " **", ".\n", "・・・", "。\r\n" ], "4": [ " ‘", " ，", " （", " ：", "・・・", "＂", "！！", "。，", " ―", "。\n\n\n\n" ], "5": [ "・・・", "＂", " ，", "。\n", "？\n", "！\n\n", "！！", "。\n\n\n\n", "。，", " …." ], "6": [ "….\n\n", "ness", "―", "**,", "’.\n\n", "‘", "ses", ".',\r\n", "**", "…”\n\n" ], "7": [ " ....\n\n", "・・・", " .\n\n", " incredible", "！\n\n", "。。\n\n", "….\n\n", "！！\n\n", "。\n\n\n\n", " …." ], "8": [ ".\n", ".\n\n\n", "…\n", "..\n", "….\n\n", "…\n\n\n", ".\n\n\n\n\n", ".\n\n\n\n", ".\n\n\n\n\n\n", " \n" ], "9": [ " canadian", " brazil", " american", " chinese", " european", " japanese", " english", " instagram", " indian", ".\n" ], "10": [ " incredible", " american", " brazil", " canadian", " fight", " amazing", " love", " european", " spanish", " great" ], "11": [ ".\n\n\n\n\n\n", ".\n", "\\/", " brazil", ".\n\n\n", " incredible", " american", " great", " canadian", " fight" ], "12": [ " people", " incredible", " love", " american", ".\n\n\n\n\n\n", ".\n\n\n", " great", " brazil", " canadian", " life" ], "13": [ ".\n", ".\n\n\n", ".\n\n\n\n\n\n", ".\n\n", " people", ".\n\n\n\n\n", " ….", " incredible", ".\n\n\n\n", "." ], "14": [ ".\n", ".\n\n\n", ".\n\n\n\n\n\n", " incredible", ".\r\n", ".\n\n", "‐", " love", " ", ".\n\n\n\n\n" ], "15": [ ".\n", "‐", ".\n\n\n\n\n\n", ".\n\n\n", ".\n\n", ".\n\n\n\n\n", ".", " love", ".\n\n\n\n", " people" ], "16": [ "‐", " love", " covid", " instagram", " people", " beautiful", " life", " jewish", " food", ".\n\n\n\n\n\n" ], "17": [ "‐", " ", "‑", ".\n\n\n\n\n\n", " love", "＂", " people", "\\/", ".\n", " beautiful" ], "18": [ "‐", ".\n", "?”", ".\n\n\n\n\n\n", "?\n", "”", "‑", "＂", "’", "”?" ], "19": [ "‐", " ", "‑", " ….", " […", "…", "….", "…\n", " people", ".\n" ], "20": [ "?”", "‐", "”?", "?\n\n\n\n\n\n", "\\/", " people", ".\n\n\n\n\n\n", "”", ".”", "\"?" ], "21": [ "?\n", "?”", "?\n\n\n", "?\n\n\n\n\n\n", "?\r\n", "?\n\n", "?\"\n", " people", ".\n", "?”\n\n" ], "22": [ "?”", "?\n\n\n\n\n\n", "?\r\n", "”?", "?\n", "?”\n\n", "?