INDEX

Explanations

ann

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

ä¸Ģæ³¢

-0.34

è·

-0.29

Vel

-0.25

ç¼©

-0.25

 Greene

-0.25

 collapsing

-0.25

Dire

-0.25

opus

-0.24

ooke

-0.24

å°ıä¼Ļ

-0.24

POSITIVE LOGITS

erman

0.31

 Frid

0.28

lander

0.27

QWidget

0.27

 serve

0.26

 newIndex

0.25

 Serve

0.25

lg

0.25

quals

0.24

 lash

0.24

Activations Density 0.004%

ann

No Comments

No Known Activations