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

ä¸¤çº§

-0.29

åıĮè¾¹

-0.26

ä¸īæĿ¡

-0.26

 irreversible

-0.25

net

-0.25

åĩĢ

-0.24

âľī

-0.24

 Åŀa

-0.24

 salv

-0.24

.fa

-0.24

POSITIVE LOGITS

coz

0.27

 Bucc

0.27

å¦ĩ

0.27

 flavored

0.25

è¿°

0.25

åİļ

0.25

é¸¬

0.25

 TestUtils

0.25

-ng

0.25

Wed

0.24

Activations Density 0.007%

No Known Activations

This feature has no known activations.