INDEX

Explanations

Text excerpts

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

byss

-0.27

åĨķ

-0.27

aped

-0.27

åĶ¤éĨĴ

-0.26

inha

-0.25

ements

-0.25

_IOS

-0.25

piv

-0.25

æµĬ

-0.25

åĿª

-0.25

POSITIVE LOGITS

è½®

0.33

 provision

0.30

imming

0.30

afa

0.30

eed

0.29

æĮīæĹ¶

0.28

 Applied

0.27

kins

0.27

Applied

0.27

ãĤĭãĤĪãģĨãģ«

0.26

Activations Density 0.022%

Text excerpts

No Comments

No Known Activations