INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ister

-0.27

æī§ä¸ļ

-0.25

æĺ¯å¯¹

-0.25

hwnd

-0.23

([\

-0.23

æįĲçĮ®

-0.23

Ø§Ø¨Ø±

-0.23

ISTER

-0.23

Ãª

-0.23

 killed

-0.23

POSITIVE LOGITS

sab

0.30

 suppose

0.27

ceptors

0.26

 nors

0.26

nim

0.24

ä¸įè®©

0.24

âĨĹ

0.24

ifth

0.23

",(

0.23

ram

0.23

Activations Density 0.227%

No Known Activations

This feature has no known activations.