INDEX

Explanations

Programming/technical discussions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

å°±ä¼ļ

-0.40

 therefore

-0.39

 consequently

-0.39

ä¹Łå°±

-0.39

éĤ£å°±

-0.36

å°±æľĥ

-0.36

 thus

-0.36

çĶ±æŃ¤

-0.36

å°±ä¸įä¼ļ

-0.35

 Consequently

-0.35

POSITIVE LOGITS

ç»ıéªĮåĴĮ

0.29

ä¼ĺè´¨çļĦ

0.29

ç»ĵ

0.28

ä¸¥æł¼çļĦ

0.27

 ç»ĵ

0.27

é¾Ł

0.26

olib

0.26

emachine

0.25

å®ŀåĬĽ

0.25

åĵĵ

0.25

Activations Density 0.000%

Programming/technical discussions

No Comments

No Known Activations