INDEX

Explanations

Processes and procedures

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

imed

-0.29

_MAKE

-0.27

ä¹Łåıªæľī

-0.25

è¿Ļæł·ä¸Ģä¸ª

-0.25

Ð³Ð¾ÑĢÐ¾Ð´

-0.25

ä¿ĿæĮģçĿĢ

-0.24

imus

-0.24

_WORDS

-0.24

('</

-0.24

bia

-0.24

POSITIVE LOGITS

å¿Ļ

0.28

æĸ¯åŁº

0.28

hart

0.26

 preparation

0.25

cene

0.25

itÃ©

0.24

Ä±yla

0.24

');

0.23

orre

0.23

neo

0.23

Activations Density 0.020%

Processes and procedures

No Comments

No Known Activations