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

flt

-0.30

æķĻå¯¼

-0.27

 alternate

-0.26

ant

-0.26

alternate

-0.25

amat

-0.25

 indefinite

-0.24

ä½ľä¸ºä¸Ģç§į

-0.24

 Antar

-0.24

reinterpret

-0.24

POSITIVE LOGITS

Cleanup

0.28

 clarity

0.26

 newObj

0.26

æī§

0.26

 Tango

0.25

abe

0.24

 phones

0.24

å¾Ĺå¤©çĭ¬åİļ

0.24

 Lair

0.24

 Whoever

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.