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

 inventive

-0.26

Ð³Ð»Ð°Ñģ

-0.24

åĩºè·¯

-0.24

æİ§èĤ¡éĽĨåĽ¢

-0.23

å¸°

-0.23

_Response

-0.23

 Peer

-0.23

dana

-0.22

éļĲçŀĴ

-0.22

çĵ¯

-0.21

POSITIVE LOGITS

åħĭèİ±

0.25

quarters

0.24

Cas

0.24

rollers

0.24

CLA

0.23

å¼¹

0.23

 kingdoms

0.23

ei

0.23

å¹¶éĿŀ

0.23

ann

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.