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

uzzi

-0.34

å®Į

-0.28

á»¯a

-0.28

æ»¡åĪĨ

-0.25

ä¸ĢåĪĩéĥ½æĺ¯

-0.25

¨

-0.25

èĪĨè®º

-0.24

 defe

-0.24

cloud

-0.24

existence

-0.24

POSITIVE LOGITS

rella

0.26

ROID

0.26

/animations

0.26

æ¬£

0.24

ationToken

0.24

à¸Ĺà¸Ńà¸Ķ

0.23

 McMahon

0.23

ospace

0.23

 chimney

0.22

iquer

0.22

Activations Density 0.110%

No Known Activations

This feature has no known activations.