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

inson

-0.29

inite

-0.27

Elk

-0.26

ä¼¸åĩº

-0.25

idad

-0.25

 Williams

-0.25

èĤ´

-0.25

 Wich

-0.25

ellular

-0.24

éģĹ

-0.24

POSITIVE LOGITS

éł

0.26

æł²

0.25

ä¸ĭåįĬåľº

0.24

yles

0.24

é¡Ĩ

0.24

strup

0.24

ç°ĩ

0.24

à¹Ģà¸ģà¸£

0.23

é©·

0.23

 scorer

0.23

Activations Density 0.041%

No Known Activations

This feature has no known activations.