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

å¾®ç¬ĳ

-0.28

heard

-0.24

,str

-0.24

æľĢå¿«

-0.24

azaar

-0.23

.onNext

-0.23

åħĪæĬĬ

-0.23

clado

-0.23

ä¼Ĺ

-0.23

ala

-0.23

POSITIVE LOGITS

ToFront

0.28

 testcase

0.25

 numerical

0.25

 manifest

0.24

åħ¬é¡·

0.24

 UIManager

0.24

 coordinates

0.23

ãģ¹ãģį

0.23

Hue

0.23

gy

0.23

Activations Density 28.231%

No Known Activations

This feature has no known activations.