INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_18.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.18.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å°±å¤ŁäºĨ

-0.26

åĲ¹

-0.26

ç»ĳå®ļ

-0.25

ãģķãģ¾

-0.25

åĳ¸

-0.25

 MASK

-0.24

 Crate

-0.24

Chief

-0.24

PRI

-0.24

Ãło

-0.24

POSITIVE LOGITS

æ²³

0.28

ael

0.27

-spec

0.26

amel

0.26

alls

0.26

 Spec

0.25

åĲ¦åĪĻ

0.25

 Gall

0.24

ais

0.24

ç«ŀèµĽ

0.24

Activations Density 17.091%

No Known Activations

This feature has no known activations.