SAE Visualizer

Index

EXPLANATIONS

职业

INFERENCE

IFRAME INTEGRATION

Direct URL

Iframe Code

<iframe src="http://localhost:3000/embed/dictionaries/qwen3-1.7b-lorsa-8x-topk64-layer0/features/279" width="100%" height="800" frameborder="0"></iframe>

NEGATIVE LOGITS

angi-13.750

ewish-13.313

.dynamic-12.938

OI-12.438

_pes-12.438

.getNext-12.375

ignal-12.250

新西-12.125

_mot-12.063

_Gee-11.875

POSITIVE LOGITS

牢17.250

_bumped16.625

STACK16.500

_outfit16.375

_Occupational16.250

ざ16.250

壁垒16.125

mlink15.875

邀15.813

公15.688

ACTIVATION TIMES 0.0725%

Activation histogram is not available.

Logits histogram is not available.

TOPACTIVATIONS

SUBSAMPLING80%

SUBSAMPLING60%

SUBSAMPLING40%

NONACTIVATING