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

æ²«

-0.28

ä¹±

-0.27

agement

-0.24

 Qual

-0.24

ä»Ģä¹Īåĳ¢

-0.24

Unc

-0.24

 Sorted

-0.24

cz

-0.24

isman

-0.24

èĪĽ

-0.24

POSITIVE LOGITS

 intervening

0.30

èµ·æºĲ

0.27

eken

0.26

DetailsService

0.26

åĽ¾çīĩæĿ¥æºĲ

0.25

peak

0.25

åĨįå¤ļ

0.25

 subt

0.25

.gms

0.25

pe

0.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.