INDEX

Explanations

article or post

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

åħ³éĹ¨

-0.28

 enhanced

-0.28

 footnote

-0.27

_FLAGS

-0.26

htdocs

-0.26

è¬ĩ

-0.26

 overall

-0.25

 seriously

-0.25

åĲ½

-0.25

æ½Ń

-0.24

POSITIVE LOGITS

 Playback

0.28

æĸ¹å¼ıè¿Ľè¡Į

0.28

ucer

0.27

Playback

0.27

æĥŃ

0.27

ciÄħ

0.26

_apply

0.25

Ã¼z

0.25

ë°©

0.25

anguages

0.24

Activations Density 0.144%

article or post

No Comments

No Known Activations