INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 prevailing

-0.28

æĢ»äº§åĢ¼

-0.27

æĶ¶åħ¥

-0.27

æ»¡

-0.27

eton

-0.26

æ´Ĺè¡£

-0.25

 Hobby

-0.25

 fulfilled

-0.25

åĨįçĶŁèĥ½æºĲ

-0.25

 Hybrid

-0.24

POSITIVE LOGITS

uco

0.28

usted

0.27

çľ¾

0.26

itel

0.26

uisse

0.26

åħ¨ä¸ĸçķĮ

0.25

 versch

0.25

çīĩåŃĲ

0.24

å¹¿å¤§ç¾¤ä¼Ĺ

0.24

 leaves

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.