INDEX

Explanations

Technical questions/answers

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

udes

-0.30

èĢķ

-0.25

anvas

-0.25

lasses

-0.24

_CE

-0.24

ISION

-0.24

ListItemIcon

-0.24

åĽłèĢĮ

-0.24

riz

-0.23

äºİæĺ¯

-0.23

POSITIVE LOGITS

not

0.67

åĲ¦

0.65

not

0.56

 Nope

0.47

Not

0.45

Not

0.45

"Not

0.44

ä¸įæĺ¯

0.42

NOT

0.42

ä¸įè¡Į

0.42

Activations Density 0.008%

Technical questions/answers

No Comments

No Known Activations