SAE Visualizer

Index

EXPLANATIONS

display => name

INFERENCE

IFRAME INTEGRATION

Direct URL

Iframe Code

<iframe src="http://localhost:3000/embed/dictionaries/qwen3-1.7b-lorsa-8x-topk64-layer0/features/61" width="100%" height="800" frameborder="0"></iframe>

NEGATIVE LOGITS

sek-13.813

CAPE-13.250

criptor-13.063

emics-13.000

ney-13.000

unga-12.500

_Blockly-12.500

yna-12.438

_pert-12.313

_%{-12.250

POSITIVE LOGITS

/screen16.000

Stand15.563

줄15.188

welcome15.000

屏14.625

-screen14.438

riteria14.250

HELL14.250

isode14.188

Hostname14.188

ACTIVATION TIMES 0.1896%

Activation histogram is not available.

Logits histogram is not available.

TOPACTIVATIONS

SUBSAMPLING80%

SUBSAMPLING60%

SUBSAMPLING40%

NONACTIVATING