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

&(

-0.28

 Crescent

-0.26

))(

-0.25

 reclaim

-0.25

&(

-0.25

.mit

-0.25

%(

-0.25

è¿ĻéĩĮæľī

-0.24

hiba

-0.24

 Sidebar

-0.24

POSITIVE LOGITS

è¿Ļä¸Ģå¤©

0.29

 automation

0.29

 sensor

0.28

èĩªåĬ¨åĮĸ

0.28

çĿĢ

0.27

ingroup

0.27

automation

0.27

Automation

0.27

sensor

0.26

åĳ¼

0.26

Activations Density 0.259%

No Known Activations

This feature has no known activations.