SAE Visualizer

Index

EXPLANATIONS

[.Millisecond] => *

INFERENCE

IFRAME INTEGRATION

Direct URL

Iframe Code

<iframe src="http://localhost:3000/embed/dictionaries/qwen3-1.7b-lorsa-8x-topk64-layer0/features/321" width="100%" height="800" frameborder="0"></iframe>

NEGATIVE LOGITS

urious-18.875

jen-17.875

emarks-16.250

uden-15.938

'</-15.750

olars-15.250

presso-15.188

ety-15.125

ständ-14.938

鞅-14.938

POSITIVE LOGITS

(se13.688

ONLY13.313

皮肤13.000

erne12.500

_Interpreter12.438

_skin12.375

润12.375

_analogue12.250

แล12.188

_roster12.063

ACTIVATION TIMES 1.1799%

Activation histogram is not available.

Logits histogram is not available.

TOPACTIVATIONS

SUBSAMPLING80%

SUBSAMPLING60%

SUBSAMPLING40%

NONACTIVATING