Span k=2, order 2, probe submarine

qwen-27blokeshe09/Qwen3.6-27B-bnb-4bitpre-4bit64 layers2026-07-14T17:15:55Unit 15

Conversation

user

Here are two things: a fern and a submarine. 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 was the vehicle. (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	200460	197220	64059	112761	106115	16168	19122	70539	202799	226543	237357	248286	234662	223805	244627	217976	28473	1

Claude's thoughts

k=2, order 2: held 1/2 [fern:2, submarine:82], co-presence 1, retrieval correct (“The submarine was the vehicle.”).

First item near rank 1, second already adrift (rank 82). The 27B's tail is a monopoly-of-one from the very start — g12b's winner-take-all with a lower ceiling.

— 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.