INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

å½¢å¼ı

-0.30

 form

-0.28

éĩįä¸Ń

-0.28

iced

-0.27

dbuf

-0.26

@↵

-0.26

 component

-0.25

phanumeric

-0.25

äººæĢ§

-0.25

CodeAt

-0.25

POSITIVE LOGITS

æŃĩ

0.29

ä¼ĳæģ¯

0.28

 Perkins

0.27

ä»ĭç»įä¸Ģä¸ĭ

0.24

 interfering

0.24

åĲİæİĴ

0.24

åģľäº§

0.24

åĺ»åĺ»

0.24

 compat

0.24

ÑģÐ°Ð´

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.