INDEX

Explanations

Code/Technical, mixed languages

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

orate

-0.30

 knees

-0.27

ktor

-0.26

iston

-0.26

æ³¨æĺİåĩºå¤Ħ

-0.25

 há»Ļ

-0.25

Tracker

-0.25

 tracker

-0.24

 Closet

-0.24

æĪ·

-0.24

POSITIVE LOGITS

ä¸Ńå¤®

0.30

çĨµ

0.30

åĪĨè§£

0.29

ViewById

0.29

åī©ä¸ĭ

0.28

æ°´å¹³

0.28

éĵ¾æĿ¡

0.27

æĬĬè¿ĻäºĽ

0.26

å¤®

0.26

Sin

0.26

Activations Density 0.001%

Code/Technical, mixed languages

No Comments

No Known Activations