INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¤ļå°ĳ

-0.28

åĽ¢

-0.26

æľįä»İ

-0.25

iÃŁ

-0.24

åľĺ

-0.24

Sou

-0.24

ycz

-0.24

 looked

-0.24

 Bosch

-0.24

 tÆ°á»Ľng

-0.24

POSITIVE LOGITS

llib

0.27

lid

0.27

GDK

0.27

 TreeSet

0.27

phalt

0.26

 ÐºÐ¾Ð¼Ð¿ÑĮÑİÑĤÐµÑĢ

0.25

 Forest

0.25

 forest

0.25

shiv

0.25

 enumerator

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.