INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itar

-0.29

åħĪåĲİ

-0.27

åĲİæĿ¥

-0.27

èį£èªī

-0.27

æĸ°çĶŁ

-0.26

oit

-0.25

eway

-0.25

 neut

-0.25

 embar

-0.25

ofi

-0.25

POSITIVE LOGITS

URNS

0.28

Dix

0.27

çī¹æľĹ

0.26

ç»ĻåŃ©åŃĲ

0.25

ç»Ļä½łä»¬

0.24

ÅĤu

0.24

lds

0.24

alse

0.24

ç»ĭ

0.23

ensem

0.23

Activations Density 13.718%

No Known Activations

This feature has no known activations.