INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

flat

-0.33

lek

-0.28

 flat

-0.26

OH

-0.25

 Flat

-0.24

eper

-0.24

rays

-0.23

ma

-0.23

arth

-0.23

SID

-0.23

POSITIVE LOGITS

 createContext

0.26

å°¼æĸ¯

0.26

oncÃ©

0.25

 presidents

0.23

ToWorld

0.23

Giz

0.23

zelf

0.23

âľķ

0.23

oubted

0.23

 griev

0.22

Activations Density 26.226%

No Known Activations

This feature has no known activations.