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

chas

-0.31

achu

-0.28

PackageName

-0.28

DataProvider

-0.26

æľºæ¢°åĮĸ

-0.25

iti

-0.25

eti

-0.24

éħĬ

-0.24

.atom

-0.24

asket

-0.24

POSITIVE LOGITS

imens

0.32

çļĦäºĭå®ŀ

0.28

à¸²à¸¢à¸Ļ

0.27

rive

0.27

éĻĢ

0.26

byn

0.26

 Crist

0.25

çļĦåĪ°æĿ¥

0.25

Cy

0.25

æĹ©æĹ©

0.25

Activations Density 0.002%

No Known Activations

This feature has no known activations.