INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_35.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.35.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 commenced

-0.29

 commence

-0.27

rophe

-0.25

ä¸ŃéĢĶ

-0.25

aremos

-0.24

çĽİ

-0.24

çīĪæĿĥ

-0.24

Ret

-0.24

/questions

-0.24

çīĪæĿĥæīĢæľī

-0.23

POSITIVE LOGITS

wat

0.30

yers

0.29

yps

0.26

onal

0.26

ç¬ĳ

0.25

tered

0.25

yper

0.25

æ´Ĺè¡£

0.25

åĸľ

0.25

è²Ķ

0.25

Activations Density 1.207%

No Known Activations

This feature has no known activations.