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

stadt

-0.27

.shtml

-0.26

utura

-0.26

 premise

-0.26

é¥²

-0.26

ottes

-0.25

.CSS

-0.25

 defaultProps

-0.25

 Rodney

-0.24

EntryPoint

-0.24

POSITIVE LOGITS

flu

0.31

è·Łä»ĸ

0.27

-US

0.27

æ°Ł

0.27

vers

0.26

egan

0.26

ObjectOfType

0.26

vised

0.26

ification

0.24

 nghá»ĭ

0.24

Activations Density 12.134%

No Known Activations

This feature has no known activations.