INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bound

-0.27

BOUND

-0.26

è´£ä»»åĪ¶

-0.25

presso

-0.24

ter

-0.24

ä»ĭ

-0.24

 shave

-0.24

obar

-0.23

å±ŀæĢ§

-0.23

Child

-0.23

POSITIVE LOGITS

 undocumented

0.28

alance

0.27

rying

0.26

à¸²à¸°

0.26

FEC

0.25

çłĸ

0.25

 yourselves

0.24

ipient

0.24

ç§ĳæĬĢèĤ¡ä»½

0.24

éĻ¢éĻ¢éķ¿

0.24

Activations Density 0.165%

No Known Activations

This feature has no known activations.