INDEX

Explanations

scientific texts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

æľªæĪĲå¹´äºº

-0.30

vod

-0.30

acity

-0.29

blink

-0.28

umer

-0.27

éĿĴå°ĳå¹´

-0.26

angs

-0.25

 youth

-0.25

lass

-0.25

 nghiá»ĩp

-0.25

POSITIVE LOGITS

 Ð·Ð°Ð¿Ð¸ÑģÐ¸

0.26

åĲĽ

0.25

hibited

0.25

RequiredMixin

0.24

 jailed

0.24

 Subscriber

0.24

EFR

0.24

 Duke

0.24

inia

0.23

 Override

0.23

Activations Density 0.937%

scientific texts

No Known Activations