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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Conditioning

-0.27

å²Ĺ

-0.27

 affirm

-0.27

æĬĢ

-0.26

ogan

-0.26

Motion

-0.24

ä¸Ńæĸ¹

-0.24

andler

-0.24

 Maiden

-0.24

'):č↵

-0.24

POSITIVE LOGITS

ScreenWidth

0.27

-screen

0.27

ree

0.26

tv

0.26

ä¸įéĢļ

0.25

ucid

0.24

Screen

0.24

ingly

0.24

loo

0.24

_screen

0.24

Activations Density 0.003%

No Known Activations

This feature has no known activations.