logitcrystal

the question

Where in depth does a transformer's next-token top-1 prediction crystallize, and does that depth follow a constant relative fraction, a constant absolute layer, or a constant distance from the last layer?

what came out

The lens top-1 is unrelated to the answer through most of depth then snaps in the last one or two layers: crystallization at layer 22.8, 26.2, 34.1 for the 24, 28, 36-layer Qwen2.5 models, always about two from the end. A tuned lens decodes no earlier. Relative-fraction versus constant-distance clock stays unresolved with three sizes.

→ read the code and re-run it