INDEX

Explanations

technical texts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

dum

-0.32

ernet

-0.28

å°ĸ

-0.27

åĺ¶

-0.26

esk

-0.26

æĥħåĨµè¿Ľè¡Į

-0.25

çĭĢ

-0.25

uyá»ĩn

-0.25

encies

-0.24

çĬ¶

-0.24

POSITIVE LOGITS

Town

0.28

 Town

0.26

 burden

0.25

-cons

0.25

ä¸Ģä¸ĸ

0.25

ØµØ¨

0.24

itage

0.23

(:,:,

0.23

 passages

0.23

á»Łi

0.23

Activations Density 0.000%

technical texts

No Comments

No Known Activations