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

 poster

-0.28

amps

-0.27

ieces

-0.26

 pÃ³

-0.26

å®¡æŁ¥

-0.25

\Active

-0.25

 Shooter

-0.25

ifter

-0.25

_stride

-0.25

.poster

-0.24

POSITIVE LOGITS

ä»Ĭå¤©æĪĳä»¬

0.28

usting

0.28

usted

0.27

hj

0.24

elay

0.24

 Pols

0.24

olls

0.24

ictory

0.23

 Svens

0.23

urre

0.23

Activations Density 0.006%

No Known Activations

This feature has no known activations.