INDEX

Explanations

computer interactions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

phins

-0.29

 indifferent

-0.27

 PHONE

-0.25

åī¯å±Ģéķ¿

-0.25

ApiResponse

-0.24

ARRIER

-0.24

bson

-0.24

à¹Ĥà¸Ħà¸£

-0.24

 Bounty

-0.24

phinx

-0.24

POSITIVE LOGITS

ä»Ģä¹Īåĳ¢

0.29

Terminal

0.26

wen

0.26

 tung

0.25

çĥŃéĹ¹

0.25

éĢīæĭ©

0.25

orida

0.25

uble

0.24

 molec

0.24

 useStyles

0.24

Activations Density 0.009%

computer interactions

No Comments

No Known Activations