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

aine

-0.27

baugh

-0.26

 useStyles

-0.26

ymm

-0.26

assword

-0.25

lsi

-0.25

è¶Ĭ

-0.25

oug

-0.24

ÑĤÑĢ

-0.24

pf

-0.24

POSITIVE LOGITS

æĶ¶

0.26

æŁ³

0.26

 Allied

0.26

ä¸Ģæ³¢

0.25

Ł¥

0.25

å¯¹æīĭ

0.25

åıĹçĽĬ

0.25

::-

0.25

è§ģ

0.25

mit

0.24

Activations Density 0.013%

No Known Activations

This feature has no known activations.