SAE Visualizer

Index

EXPLANATIONS

[Med] => [suffix]

INFERENCE

IFRAME INTEGRATION

Direct URL

Iframe Code

<iframe src="http://localhost:3000/embed/dictionaries/qwen3-1.7b-lorsa-8x-topk64-layer0/features/191" width="100%" height="800" frameborder="0"></iframe>

NEGATIVE LOGITS

.Elements-19.500

izedName-19.375

潮流-18.500

太久-17.875

FFE-17.375

Tpl-17.250

新西-17.250

看电影-16.875

kers-16.125

_ELEM-16.125

POSITIVE LOGITS

este14.688

�14.063

_]13.438

_)13.063

理13.000

ven13.000

using12.813

身心健康12.563

钵12.375

RI12.250

ACTIVATION TIMES 0.0989%

Activation histogram is not available.

Logits histogram is not available.

TOPACTIVATIONS

SUBSAMPLING80%

SUBSAMPLING60%

SUBSAMPLING40%

NONACTIVATING