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

kah

-0.28

errat

-0.27

chos

-0.27

éĹ·

-0.26

setEnabled

-0.25

æ²¡è§ģè¿ĩ

-0.24

.pe

-0.24

-bottom

-0.24

åºķ

-0.24

IFE

-0.24

POSITIVE LOGITS

æ®ĩ

0.29

DataContext

0.29

çĤĬ

0.25

 Marathon

0.24

ynamics

0.24

åľ¨è¿ĩåİ»

0.24

æĹĹ

0.23

ä¹ĭäºº

0.23

olie

0.23

mitters

0.22

Activations Density 52.468%

No Known Activations

This feature has no known activations.