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

Sharper

-0.33

 subject

-0.28

 locator

-0.27

éĽ¨

-0.27

san

-0.26

fall

-0.26

.subject

-0.25

#%

-0.25

 complet

-0.24

 stitch

-0.24

POSITIVE LOGITS

mue

0.28

æ¡Ĥ

0.25

éĺĻ

0.25

å¼¯æĽ²

0.25

rowse

0.25

ndo

0.24

pg

0.24

ounded

0.24

 crypt

0.24

controlled

0.24

Activations Density 0.003%

No Known Activations

This feature has no known activations.