SAE Visualizer

Index

EXPLANATIONS

[health] => [related]

INFERENCE

IFRAME INTEGRATION

Direct URL

Iframe Code

<iframe src="http://localhost:3000/embed/dictionaries/qwen3-1.7b-lorsa-8x-topk64-layer0/features/140" width="100%" height="800" frameborder="0"></iframe>

NEGATIVE LOGITS

efe-14.563

ewing-14.438

indr-14.250

nga-13.563

ęd-13.500

.extent-12.875

말-12.750

ussen-12.563

_ICC-12.500

ing-12.438

POSITIVE LOGITS

身体健康19.500

_health17.375

_healthier17.250

项目建设17.125

选择了16.125

健康16.000

山区15.750

健康的15.625

白衣15.438

:end15.313

ACTIVATION TIMES 0.1722%

Activation histogram is not available.

Logits histogram is not available.

TOPACTIVATIONS

SUBSAMPLING80%

SUBSAMPLING60%

SUBSAMPLING40%

NONACTIVATING