INDEX

Explanations

technical documents/emails

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

å¯¹å¾ħ

-0.29

 Hang

-0.28

åĲģ

-0.28

gan

-0.26

æĸ¥

-0.26

 transfer

-0.25

 relationship

-0.24

 Cant

-0.23

ä¸Ģæ®µ

-0.23

åĲĵ

-0.23

POSITIVE LOGITS

olean

0.25

lords

0.25

æµģè½¬

0.25

 Covent

0.25

åħ¼

0.25

aptive

0.25

å¼¥

0.25

APT

0.24

.Resume

0.24

èµĦæĸĻ

0.23

Activations Density 0.000%

technical documents/emails

No Comments

No Known Activations