INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.unwrap

-0.29

åħĶ

-0.28

pell

-0.27

imately

-0.27

rÃ³

-0.27

éĿĸ

-0.26

èĦ±ç¦»

-0.25

 GOOGLE

-0.24

ä¸»ä¸ļ

-0.24

aways

-0.23

POSITIVE LOGITS

inge

0.29

 materia

0.27

/articles

0.26

Ã¸re

0.26

æłı

0.25

æİ¨

0.24

Hour

0.24

verting

0.23

ÃŁe

0.23

&w

0.23

Activations Density 0.015%

No Known Activations

This feature has no known activations.