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

dÃ¬

-0.29

ertz

-0.28

onomy

-0.26

æ±ĩ

-0.25

“He

-0.24

 sling

-0.23

ä¸

-0.23

 lives

-0.23

åľ°ä¸Ĭ

-0.23

ç³»ç»Ł

-0.23

POSITIVE LOGITS

anas

0.25

çİ°åĩº

0.24

èĲ¼

0.24

.nav

0.24

å±ķçİ°åĩº

0.24

vertising

0.23

æ±¶

0.22

åıĺåİĭ

0.22

eos

0.22

eos

0.22

Activations Density 0.003%

No Known Activations

This feature has no known activations.