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

Negative Logits

éĢļçŁ¥

-0.30

chnitt

-0.28

 centres

-0.26

 buddy

-0.26

istra

-0.26

æľīåĬ©

-0.26

è°ĥéħį

-0.25

Notification

-0.25

notation

-0.25

å´¤

-0.25

POSITIVE LOGITS

obile

0.29

inated

0.29

.TryParse

0.27

ĵ

0.26

inati

0.25

-License

0.25

odom

0.24

 carpets

0.24

quals

0.24

nection

0.24

Activations Density 2.983%

No Known Activations

This feature has no known activations.