INDEX

Explanations

as

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

PEND

-0.28

ernity

-0.27

ĭè¯ķ

-0.25

çıĳ

-0.25

çľ¼éķľ

-0.25

iÃ©n

-0.25

erculosis

-0.24

credits

-0.24

 coupe

-0.24

æĥ³è±¡åĬĽ

-0.24

POSITIVE LOGITS

ITT

0.30

ĥĿ

0.28

wire

0.28

ilha

0.27

ä¸ĢåŃĹ

0.26

æįŁ

0.25

 News

0.24

à¸Ľà¸£à¸°à¸ªà¸ĩ

0.24

 Expl

0.24

æĹłç§ģ

0.24

Activations Density 0.000%

as

No Comments

No Known Activations