INDEX

Explanations

of

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

addock

-0.27

 Comet

-0.25

ossip

-0.25

 Sussex

-0.25

 Goose

-0.25

ä½¿äºº

-0.25

 academics

-0.24

phet

-0.24

QRSTUV

-0.24

-eff

-0.24

POSITIVE LOGITS

Ain

0.28

cker

0.27

 precaution

0.26

ergic

0.25

Ã¡ln

0.25

Ãªncias

0.25

 ÄĳÃ¡nh

0.24

ila

0.24

<AM

0.24

æ£®

0.24

Activations Density 0.038%

of

No Comments

No Known Activations