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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Baker

-0.30

 liter

-0.29

 tabletop

-0.28

 baked

-0.27

à¸Ĳ

-0.26

zug

-0.26

å¾Ģä¸ĭ

-0.26

.ht

-0.25

 arrested

-0.24

 Fair

-0.24

POSITIVE LOGITS

åĶ±æŃĮ

0.33

estro

0.28

oga

0.27

å§Ķä¼ļ

0.26

æľªæĪĲå¹´äºº

0.26

çļĦåĪ°æĿ¥

0.25

unto

0.25

åī§

0.25

wagon

0.25

 prayers

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.