INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_35.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.35.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĹģè¾¹çļĦ

-0.27

èħĭ

-0.26

_/

-0.25

çķĻè¨Ģ

-0.25

**

-0.24

ç½²

-0.24

ä¸ªäººè§ĤçĤ¹

-0.24

rieg

-0.23

ç¼¨

-0.23

POSITIVE LOGITS

bourg

0.28

bur

0.27

idges

0.27

 boards

0.26

 worst

0.26

lac

0.25

 Second

0.25

 colored

0.25

ominated

0.25

çļĦä¼Łå¤§

0.25

Activations Density 0.615%

No Known Activations

This feature has no known activations.