INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åľĪ

-0.28

 Enjoy

-0.26

erin

-0.25

wizard

-0.25

é¢Ħè®¡

-0.25

 TObject

-0.24

çī§

-0.24

é«ĺæīĭ

-0.24

orsche

-0.24

 Cheer

-0.24

POSITIVE LOGITS

joined

0.30

 bilateral

0.27

 Metro

0.27

æİ¥è½¨

0.26

 Alle

0.25

ilen

0.25

æ¼

0.25

.OrderByDescending

0.25

 joined

0.25

 Flux

0.25

Activations Density 0.009%

No Known Activations

This feature has no known activations.