SAE Visualizer

Index

EXPLANATIONS

[immune] => [system]

INFERENCE

IFRAME INTEGRATION

Direct URL

Iframe Code

<iframe src="http://localhost:3000/embed/dictionaries/qwen3-1.7b-lorsa-8x-topk64-layer0/features/298" width="100%" height="800" frameborder="0"></iframe>

NEGATIVE LOGITS

_Stream-14.125

_betrayal-13.813

袭-13.750

Stream-13.750

亲-13.313

一步-13.188

迁移-13.125

_chu-13.000

奠基-12.500

_Amber-12.375

POSITIVE LOGITS

metic15.438

ownt15.313

сол15.188

ederation15.188

лей14.938

edImage14.750

crest14.625

кри14.438

(proj14.438

onio14.313

ACTIVATION TIMES 0.0805%

Activation histogram is not available.

Logits histogram is not available.

TOPACTIVATIONS

SUBSAMPLING80%

SUBSAMPLING60%

SUBSAMPLING40%

NONACTIVATING