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

à¸¥à¸²

-0.27

æī¼

-0.27

adge

-0.26

 binding

-0.25

è¾«

-0.25

 systemic

-0.25

CHR

-0.24

binding

-0.24

å¸¦ä¸Ĭ

-0.24

spread

-0.24

POSITIVE LOGITS

sec

0.28

ONUS

0.27

Sec

0.26

Lon

0.26

Lon

0.26

san

0.26

Ð´ÑĥÑĤ

0.26

nis

0.26

Sec

0.25

SEC

0.25

Activations Density 0.001%

No Known Activations

This feature has no known activations.