INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_35.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.35.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

agus

-0.29

ino

-0.25

 ambassador

-0.25

afs

-0.24

acles

-0.24

er

-0.24

ä½ıåľ¨

-0.24

—

-0.24

åįĹçľģ

-0.24

ampus

-0.24

POSITIVE LOGITS

 Totally

0.25

\"{

0.24

 itemView

0.24

 Procedures

0.24

æľīæĽ´å¥½çļĦ

0.24

 Units

0.24

.UnitTesting

0.24

æŁľåı°

0.23

è¿¢

0.23

Equ

0.23

Activations Density 12.491%

No Known Activations

This feature has no known activations.