INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é«ĺåİŁ

-0.27

ARIO

-0.26

ROME

-0.26

åıĳå±ķåīįæĻ¯

-0.24

 dangers

-0.24

ç´łè´¨æķĻèĤ²

-0.24

çĦĵ

-0.24

gio

-0.24

çĩĥæĸĻ

-0.24

æĥľ

-0.24

POSITIVE LOGITS

æĮĩ

0.29

 imperfect

0.28

æİ§èĤ¡éĽĨåĽ¢

0.28

ä¸įå®Į

0.26

RuleContext

0.26

imax

0.26

 motion

0.25

irst

0.25

ìĽĥ

0.25

rows

0.25

Activations Density 1.063%

No Known Activations

This feature has no known activations.