INDEX

Explanations

brain

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ece

-0.26

åĨ·éĿĻ

-0.24

è¿ľ

-0.24

 =↵↵

-0.23

å¼ĢæĪĺ

-0.23

Seen

-0.23

.forRoot

-0.23

 Ð¸Ð½ÑĦÐ¾ÑĢÐ¼Ð°ÑĨÐ¸Ñı

-0.23

portun

-0.23

æŁ¥çľĭåħ¨æĸĩ

-0.23

POSITIVE LOGITS

å®ļä½į

0.29

.sl

0.27

 second

0.26

è®¢éĺħ

0.25

æįı

0.25

åı¯ä»¥è¯´

0.25

ç¬¬äºĮ

0.25

çļĦçĽ®çļĦ

0.25

second

0.24

DeV

0.24

Activations Density 0.002%

brain

No Comments

No Known Activations