INDEX

Explanations

storytelling

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

acÄ±

-0.27

bac

-0.24

dib

-0.24

å¸®

-0.24

çĻ¾ç§ĳ

-0.23

.listFiles

-0.23

asters

-0.23

bug

-0.23

ollections

-0.23

éªļ

-0.23

POSITIVE LOGITS

 never

0.60

åĨįä¹Łæ²¡æľī

0.55

åĨįä¹Łä¸į

0.52

æ°¸ä¸į

0.52

ä¸įä¼ļåĨį

0.51

ä¸įåĨį

0.50

 NEVER

0.49

never

0.47

 Never

0.47

Never

0.45

Activations Density 0.005%

storytelling

No Comments

No Known Activations