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

Negative Logits

ewise

-0.28

ove

-0.26

wise

-0.24

ç»

-0.24

orelease

-0.24

ierre

-0.24

ovsky

-0.23

/Peak

-0.23

ergy

-0.23

ALLOW

-0.23

POSITIVE LOGITS

æµħ

0.26

ban

0.26

cff

0.26

 èĩ

0.24

SCO

0.24

jn

0.24

ä¿¯

0.24

cf

0.23

avenport

0.23

 parte

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.