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

ĥĿ

-0.29

ä¿Ŀ

-0.27

çĿĢ

-0.25

eof

-0.25

listeners

-0.24

-Origin

-0.23

-im

-0.23

 glfw

-0.23

aises

-0.23

ä¾µå®³

-0.23

POSITIVE LOGITS

Anonymous

0.28

æ¨¡åŀĭ

0.28

avern

0.27

Ĳľç´¢

0.26

 Model

0.25

ava

0.25

%(

0.24

Ath

0.24

 Anonymous

0.24

ç½ħ

0.24

Activations Density 0.032%

No Known Activations

This feature has no known activations.