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

æį¢

-0.31

æį¢æĪĲ

-0.27

 EVER

-0.25

.returnValue

-0.25

ä»£è¡¨

-0.25

è·³åĩº

-0.24

á»Ĩ

-0.24

æį¢ä¸ª

-0.24

å£«

-0.24

Ø§Ø·

-0.24

POSITIVE LOGITS

Ã±ana

0.29

(&$

0.28

åħ±äº§åħļåĳĺ

0.28

.TryParse

0.27

_weak

0.27

ignKey

0.27

&a

0.26

_paper

0.26

becue

0.25

ieÅ¼

0.25

Activations Density 0.001%

No Known Activations

This feature has no known activations.