INDEX

Explanations

News/story snippets

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

å¢ŀåĢ¼æľįåĬ¡

-0.27

èĤ¡æĿĥæĬķèµĦ

-0.26

å¤±æľĽ

-0.26

ä¹Ĺ

-0.26

obs

-0.25

<small

-0.25

iÃ¨res

-0.24

sville

-0.24

 multip

-0.24

acted

-0.24

POSITIVE LOGITS

ny

0.30

ucson

0.28

ny

0.26

åľ¨å¤ĸ

0.26

çĸĨ

0.26

ozy

0.26

 hann

0.26

NY

0.25

 digs

0.25

isel

0.25

Activations Density 0.315%

News/story snippets

No Comments

No Known Activations