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

åĩĨå¤ĩå·¥ä½ľ

-0.28

æ¨Ĺ

-0.26

lernen

-0.26

 tats

-0.25

Chapter

-0.25

 Chapters

-0.25

AMES

-0.25

 nextState

-0.25

 prive

-0.25

åĩĨå¤ĩå¥½

-0.24

POSITIVE LOGITS

çļĦè®¤åı¯

0.28

ffect

0.27

å¤ªå¤ļäºĨ

0.26

greg

0.25

åı³ä¾§

0.25

emand

0.25

çļĦå½±åĵį

0.24

æ²³æ°´

0.24

è¹Ĭ

0.24

Pod

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.