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

å³Ń

-0.27

é¥±åĴĮ

-0.27

ucher

-0.26

 pneumonia

-0.26

åħ¸

-0.24

 getContent

-0.24

CONTENT

-0.24

ataire

-0.24

 lá»Ĺi

-0.24

 alike

-0.23

POSITIVE LOGITS

heim

0.31

oley

0.29

çļĦæĿĥåĪ©

0.28

rap

0.26

POS

0.25

ä¹Ŀå¤§

0.24

 Coins

0.24

QA

0.24

çļĦéĢīæĭ©

0.24

utow

0.24

Activations Density 0.006%

No Known Activations

This feature has no known activations.