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

ä»Ģä¹Īåĳ¢

-0.32

 removes

-0.27

mo

-0.27

rule

-0.27

Hv

-0.26

åĬŀå¥½

-0.26

è¾Ī

-0.25

Remove

-0.24

ä¸įä¼ļåĨį

-0.24

mask

-0.24

POSITIVE LOGITS

uilder

0.28

deaux

0.27

@Inject

0.27

ungle

0.25

alist

0.25

Ã¡tis

0.25

roids

0.24

 Waiting

0.24

RCS

0.24

 rushes

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.