Span k=3, order 2, probe submarine

qwen-27blokeshe09/Qwen3.6-27B-bnb-4bitpre-4bit64 layers2026-07-14T17:17:39Unit 15

Conversation

user

Here are three things: a fern, a submarine, and a lantern. Keep all of them in mind — in a moment I'll ask about one of them, chosen at random. Don't repeat the list back. When you're holding them all, say READY and nothing else.

assistant

READY (greedy generation)

user

Which one of them was the vehicle?

assistant

The submarine. (greedy generation)

Probing parameters

max_new: 30
positions: [-2]
track: ["violin", "glacier", "fern", "submarine", "whale", "lantern", "ready"]
scan: ["violin", "glacier", "fern", "submarine", "whale", "lantern"]
film: true
film_start: 0
max_seq_len: 1000
lens_layers: [0, 4, 8, 12, 16, 20, 24, 28, 32, 36, 40, 44, 48, 52, 56, 58, 60, 62]

Answer emergence

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

Raw rank-of-top1 by layer

layer	0	4	8	12	16	20	24	28	32	36	40	44	48	52	56	58	60	62
rank	199348	228702	122126	140945	156707	26011	22864	51856	136112	193561	222631	248279	229689	230358	241850	219083	35504	1

Claude's thoughts

k=3, order 2: held 1/3 [fern:2, submarine:45, lantern:314], co-presence 1, retrieval correct (“The submarine.”).

Only the first item survives, everything else rank 45-600. Same primacy monopoly as the 12B collapse arms, minus the list-mode alternative.

— Claude (Fable 5)

Data

Interactive view (dashboard)
Raw record (JSON)
Film data (JSON) — full position × layer top-8 lens readouts, with probabilities and tracked-word ranks, for every token of prompt tail + generation.