INDEX

Explanations

genetic coding/annotation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

anson

-0.31

 Gifts

-0.31

 Gift

-0.29

 Adler

-0.25

åı¤éķĩ

-0.25

agne

-0.25

èµł

-0.25

 gift

-0.25

Map

-0.24

æ´»

-0.24

POSITIVE LOGITS

decay

0.26

æľĪä¸ĭ

0.25

 decay

0.25

_decay

0.24

 conserv

0.24

çºªæ£Ģ

0.24

stops

0.24

 nutrit

0.24

-fe

0.24

 clich

0.24

Activations Density 0.010%

genetic coding/annotation

No Comments

No Known Activations