INDEX

Explanations

scientific writing

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

 history

-0.26

 Daily

-0.25

éļĹ

-0.25

 Tender

-0.24

 Boot

-0.24

éģĩåĪ°äºĨ

-0.24

 History

-0.24

 pear

-0.23

 Weekly

-0.23

å¥Ń

-0.23

POSITIVE LOGITS

ä»Ģä¹Īåĳ¢

0.32

ä¸įåģľ

0.27

arlo

0.27

anzi

0.26

getParam

0.26

å¤§å®¶åı¯ä»¥

0.26

plen

0.26

ToF

0.26

ä¸įè¶³

0.26

ä¸Ģä»¶

0.25

Activations Density 0.001%

scientific writing

No Comments

No Known Activations