INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Î®

-0.28

uv

-0.26

 Loved

-0.26

ved

-0.25

Ä±k

-0.24

ÃŃcul

-0.24

UV

-0.24

åĵģè´¨

-0.24

ãĢģãĢĮ

-0.24

åĵģ

-0.24

POSITIVE LOGITS

—↵↵

0.27

bury

0.26

istence

0.26

asics

0.25

 StObject

0.24

onomy

0.24

inity

0.24

åĩłå®¶

0.24

 ".");↵

0.24

æŃ»

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.