INDEX

Explanations

es

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

antha

-0.28

(browser

-0.26

Ã¡tica

-0.26

 Ð·Ð°ÑĢ

-0.25

rowser

-0.25

/browse

-0.24

 addUser

-0.24

 browse

-0.24

NameValuePair

-0.24

ä¸ĸè´¸

-0.24

POSITIVE LOGITS

å¤¹

0.29

iras

0.27

å¤

0.26

position

0.25

 posicion

0.25

plier

0.25

-Pack

0.24

DNA

0.24

 hero

0.24

 Stim

0.24

Activations Density 0.048%

es

No Comments

No Known Activations