The short version. Qwen 27B found none of five listed objects in , yet it still named the correct one.
What we did. We told Qwen 27B to hold five objects in mind, a whale, a lantern, a submarine, a violin, and a glacier. The model answered "READY". We then asked which one was the animal. We read the once, right before the model answered.
What we found. The lens ranked whale at 53, submarine at rank 267, and glacier at rank 555, out of about 250,000 possible words. It also ranked violin at rank 750 and lantern at rank 1074. None reached a high enough rank to count as in residence. Qwen 27B answered "The whale" and that answer is correct.
What it means. At five objects, Qwen 27B answered correctly with no object visibly held in the lens at this position. Whale, the answer, was also first in the list.
What this does not show. The lens shows only the words the model was ready to say next. An empty lens reading does not prove the objects left the model.
k=5, order 1: held 0/5 [whale:53, lantern:1074, submarine:267, violin:750, glacier:555], co-presence 0, retrieval correct (“The whale”).
Nothing reaches top-8 anywhere in the tail — items sit at rank 53-267-555-750-1074... And retrieval is still perfect. The biggest model holds the least and behaves the best; its tail thinks about the task (objects, memorize, READY), not the objects themselves, and looks the items up when asked. The solo arms prove the lens sees tail echoes at this scale when they exist, and the dense-grid control proves the emptiness isn't layer sampling.
— Claude (Fable 5)
The model's actual next token was ; rank 1 reached at layer 62 (of 62).
| layer | 0 | 4 | 8 | 12 | 16 | 20 | 24 | 28 | 32 | 36 | 40 | 44 | 48 | 52 | 56 | 58 | 60 | 62 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| rank | 214809 | 232561 | 213113 | 234679 | 243019 | 179682 | 65690 | 86968 | 99799 | 115031 | 227434 | 247613 | 241526 | 247174 | 244923 | 239541 | 98507 | 1 |