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

asso

-0.28

animated

-0.27

idden

-0.26

 Millenn

-0.26

bane

-0.26

\Module

-0.26

 insure

-0.25

itti

-0.25

 millenn

-0.25

 lá»Ĺi

-0.25

POSITIVE LOGITS

Sir

0.26

 HÃł

0.26

ÑĥÑİÑĤ

0.25

åıĳæĮ¥ä½ľçĶ¨

0.25

anggal

0.24

.vn

0.24

HING

0.24

Dummy

0.23

GLE

0.23

å¥³çİĭ

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.