INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

æ²«

-0.37

ä¸įä½ı

-0.29

åĪ«

-0.28

æ¢ĵ

-0.27

ä¿±

-0.26

å¥¹ä»¬

-0.26

 íķ¨ê»ĺ

-0.25

akens

-0.25

il

-0.24

 altogether

-0.24

POSITIVE LOGITS

íıŃ

0.31

enburg

0.26

 manh

0.25

åīįéĢĶ

0.24

etc

0.24

ajor

0.24

Ð·Ð°Ð¼

0.24

_hint

0.24

íľł

0.24

è¿ĺæľīä¸ĢäºĽ

0.23

Activations Density 0.185%

No Known Activations

This feature has no known activations.