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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icks

-0.29

æİĪ

-0.28

@m

-0.26

ç½ĳæł¼

-0.26

åħ¨éĿ¢

-0.26

iosk

-0.25

ty

-0.25

ç¦»

-0.25

éĩĳå¸ģ

-0.24

åħ¨éĿ¢æıĲåįĩ

-0.24

POSITIVE LOGITS

 extremes

0.28

stripe

0.27

afs

0.26

 stripe

0.26

 pozosta

0.25

icum

0.25

createView

0.25

icus

0.25

alerts

0.25

 Fits

0.24

Activations Density 0.010%

No Known Activations

This feature has no known activations.