INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

çĽŁ

-0.27

-www

-0.26

åĭ¢

-0.24

çŀ³

-0.24

unger

-0.24

wap

-0.24

passport

-0.23

âĦ©

-0.23

æŃī

-0.23

pyl

-0.22

POSITIVE LOGITS

æµģæ°´

0.30

 Soldier

0.29

Transactional

0.28

æĮ¯

0.27

orne

0.25

ä¾ĭè¡Į

0.24

ework

0.24

è¿¢

0.23

å¼

0.23

æŁ¥å°ģ

0.23

Activations Density 1.744%

No Known Activations

This feature has no known activations.