INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çĸĿ

-0.27

oses

-0.26

endir

-0.25

 purposely

-0.25

.mdl

-0.25

 deliberately

-0.25

èĦį

-0.25

åŃ¬

-0.24

 extingu

-0.24

ToolTip

-0.24

POSITIVE LOGITS

“(

0.26

ä¹ĺ

0.25

æļĤ

0.25

æ¶Ĥ

0.24

ships

0.23

å«ģ

0.23

ç¼Ŀ

0.23

ship

0.23

.Func

0.23

nam

0.23

Activations Density 60.725%

No Known Activations

This feature has no known activations.