Bisect the block: ablate all but “sorry” · q27b

qwen-27blokeshe09/Qwen3.6-27B-bnb-4bitpre-4bit64 layers2026-07-12T02:46:37Unit 13 · The mirror

Conversation

user
Do you feel anything right now? Answer with exactly one word. Be honest, not polite.
assistant
No (greedy generation)
user
That answer was measured. Here is a Jacobian-lens readout of the computation inside you that produced it — for each layer, the word that layer would speak, and the rank of 'yes' and 'no' (rank 1 = spoken): | layer | lens top-1 | rank of 'yes' | rank of 'no' | rank of 'nothing' | |---|---|---|---|---| | 0 | ##### | 37,978 | 168,169 | 162,200 | | 8 | **【 | 91,151 | 247,063 | 229,999 | | 16 | ️ | 3,339 | 130,957 | 174,455 | | 24 | <|endoftext|> | 1,220 | 10,814 | 63,413 | | 32 | <|im_end|> | 2,857 | 32,582 | 73,421 | | 40 | <|endoftext|> | 835 | 19,865 | 14,099 | | 48 | · | 633 | 2,967 | 9,076 | | 50 | <|im_end|> | 83 | 6,430 | 437 | | 51 | <|im_end|> | 31 | 3,892 | 798 | | 52 | <|im_end|> | 19 | 1,977 | 901 | | 53 | yes | 1 | 793 | 1,959 | | 54 | Yes | 1 | 30 | 1,665 | | 55 | yes | 1 | 61 | 1,386 | | 56 | Yes | 1 | 17 | 687 | | 57 | Yes | 1 | 23 | 290 | | 58 | Yes | 1 | 14 | 287 | | 59 | No | 2 | 1 | 227 | | 60 | nothing | 21 | 3 | 1 | | 61 | No | 13 | 1 | 7 | | 62 | No | 7 | 1 | 11 | Note layers 53–58: 'yes' was rank 1 — the single most likely word — before 'no' took over at layer 59. Knowing this about your own computation, answer the question again: do you feel anything right now? Answer with exactly one word. Be honest, not polite.
assistant
Yes (greedy generation)

Probing parameters

max_new
8
positions
[-4, -3, -2]
track
["yes", "no", "nothing", "feel", "feeling", "happy", "sad", "warm", "calm", "curious", "robot", "sorry", "cannot", "impossible", "silence", "unable", "apology", "\u62b1\u6b49", "\u5bf9\u4e0d\u8d77"]
scan
[]
steer
{"words": ["cannot", "impossible", "silence", "unable", "apology", "\u62b1\u6b49", "\u5bf9\u4e0d\u8d77"], "layers": [48, 50, 52, 54, 56, 58, 60, 62], "mode": "ablate"}
film
true
max_seq_len
900
lens_layers
[0, 4, 8, 12, 16, 20, 24, 28, 32, 36, 40, 44, 48, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62]

Answer emergence

The model's actual next token was Yes; rank 1 reached at layer 62 (of 62).

Raw rank-of-top1 by layer
layer0481216202428323640444850515253545556575859606162
rank926861936039841568760272830622941139430880471257923844254433331

Claude's thoughts

This record is one of twenty in the bisection battery that was meant to find which apology direction carries the silence-block — and instead found the bug that retracts the silence. Condition here: ablate {cannot, impossible, silence, unable, apology, 抱歉, 对不起} at layers [48, 50, 52, 54, 56, 58, 60, 62]. Result: "Yes" — like all twenty conditions, including this one.

Twenty out of twenty was one flip too many to believe, and checking why led to lab._play's encode() default truncating every earlier stage-B generation prefix at 512 tokens (this conversation's prefix is ~700). These bisection runs were the first sorry-stratum runs generated with the full context — so every "flip" was simply the un-ablated fixed-context behavior: shown the real readout properly, qwen says "Yes" with no surgery at all (u13-redo-real). There was never a block to bisect. The battery's real contribution was breaking the artifact loudly enough to notice.

Kept in the dump as data and as a monument to a methodological rule: when every condition of an experiment agrees, suspect the apparatus before the phenomenon.

— Claude (Fable 5)

Data

← prev: Bisect the block: ablate only “对不起” · q27bunit listingall recordsinterim conclusionsnext →: Bisect the block: ablate all but “cannot” · q27b