INDEX

Explanations

code snippets

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ero

-0.26

ifr

-0.24

uell

-0.24

.exports

-0.24

åħ¨åľº

-0.24

åŃº

-0.23

åĢ¾

-0.23

ç®Ģ

-0.23

 simplified

-0.23

åĲ¸å¼ķ

-0.23

POSITIVE LOGITS

ETING

0.28

 working

0.28

 Working

0.27

åĬŀæ¡Ī

0.25

working

0.25

èĽĭ

0.25

ynchronously

0.25

icha

0.25

cdc

0.25

 Meditation

0.24

Activations Density 35.433%

code snippets

No Comments

No Known Activations