INDEX

Explanations

science

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

èĢĮåİ»

-0.27

ishly

-0.27

 ratios

-0.26

iously

-0.26

alent

-0.26

Lens

-0.25

arent

-0.25

ationally

-0.24

ATIC

-0.24

hots

-0.23

POSITIVE LOGITS

 civilizations

0.28

civil

0.27

 civilization

0.26

ceu

0.26

æī¿æĭħè´£ä»»

0.25

IU

0.25

IXEL

0.25

ç¨·

0.24

è§£åĨ³éĹ®é¢ĺ

0.24

åĿ¼

0.24

Activations Density 0.002%

science

No Comments

No Known Activations