INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Judges

-0.27

 allied

-0.26

NullException

-0.26

à¸«à¸§

-0.25

OBS

-0.24

oodles

-0.24

ãģ«åĩº

-0.24

AutoSize

-0.23

å®ļä»·

-0.23

 Rebels

-0.23

POSITIVE LOGITS

track

0.29

 mass

0.28

vac

0.27

rush

0.26

mass

0.26

localized

0.25

UNUSED

0.25

irut

0.25

 track

0.25

ä¸ĺ

0.24

Activations Density 0.018%

No Known Activations

This feature has no known activations.