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

@g

-0.28

ongs

-0.26

Bay

-0.26

åĩ¤åĩ°

-0.26

bay

-0.26

-sensitive

-0.26

åıĸ

-0.25

åı¦

-0.25

Bay

-0.25

ball

-0.24

POSITIVE LOGITS

éĿŀæ´²

0.26

 yourselves

0.25

 African

0.24

âĢĽ

0.24

 anmeld

0.24

åıĹè®¿

0.24

çĿ£åĬŀ

0.24

çķļ

0.24

ç¤¾ä¼ļèµĦæľ¬

0.24

gere

0.23

Activations Density 0.199%

No Known Activations

This feature has no known activations.