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

)t

-0.25

ä¸ªé¡¹çĽ®

-0.25

æıĲèµ·

-0.25

æİĩ

-0.24

åĽ½èµĦ

-0.24

ãĥįãĤ¿

-0.24

lov

-0.24

SAT

-0.24

 descend

-0.23

*w

-0.23

POSITIVE LOGITS

ç§°ä¹ĭ

0.31

ushman

0.29

canf

0.28

æĦıå¤ĸ

0.27

ants

0.26

ilateral

0.26

hec

0.25

olis

0.25

ç§°

0.25

iants

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.