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

sto

-0.28

 none

-0.27

EC

-0.27

æĢĿ

-0.26

 None

-0.26

Ð±Ð°ÑĢ

-0.26

 styled

-0.25

ering

-0.25

none

-0.25

çº³æĸ¯

-0.25

POSITIVE LOGITS

ä¸įèī¯ä¿¡æģ¯

0.26

-separated

0.25

 HÃ¶he

0.25

æĿ¥åİĨ

0.25

 unsus

0.24

ussed

0.24

pear

0.24

_parsed

0.23

avig

0.23

æĿ¥èĩª

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.