INDEX

Explanations

attention

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

ded

-0.31

çĻ»

-0.27

¨¡

-0.25

Ded

-0.25

 çĻ»

-0.25

ded

-0.24

åįĥåħĥ

-0.24

orks

-0.24

Ã¢m

-0.24

eng

-0.24

POSITIVE LOGITS

çĶŁéķ¿

0.29

-growing

0.27

IOC

0.27

commission

0.26

growth

0.24

Commission

0.24

 Growing

0.24

 ports

0.24

Portrait

0.24

 forecasts

0.24

Activations Density 0.003%

attention

No Comments

No Known Activations