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

èķĻ

-0.31

 táº¡p

-0.28

lander

-0.25

ugi

-0.25

-thumbnail

-0.25

æĮŁ

-0.24

åĲ»

-0.24

Asi

-0.24

lag

-0.24

ç»ª

-0.23

POSITIVE LOGITS

xDE

0.27

ä¸īå¤©

0.26

 eternal

0.26

à¹Ģà¸ªà¸£

0.26

dz

0.25

ocyte

0.25

arts

0.24

ä»£

0.24

ierte

0.24

 maths

0.24

Activations Density 1.146%

No Known Activations

This feature has no known activations.