INDEX

Explanations

between two things

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çĲĨè§£åĴĮ

-0.30

éºĿ

-0.28

æĺ¯éĿŀ

-0.27

imony

-0.25

åĩĨ

-0.25

ðŁĲ¶

-0.25

åķģ

-0.25

rzy

-0.25

*cos

-0.24

ething

-0.24

POSITIVE LOGITS

çģ¶

0.35

fac

0.32

Fac

0.29

Fac

0.29

tl

0.27

IBUTES

0.27

anel

0.27

enc

0.27

 From

0.26

nc

0.26

Activations Density 0.048%

between two things

No Comments

No Known Activations