INDEX

Explanations

positive outcomes and living well

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

Vig

-0.27

Omn

-0.26

íĥĿ

-0.26

æŀ¶

-0.26

 Skinner

-0.25

'{}

-0.25

metric

-0.25

 è¾ĵ

-0.25

é¸¨

-0.25

è¾ĵ

-0.25

POSITIVE LOGITS

eland

0.26

å°ĳ

0.26

 aure

0.24

uzu

0.24

ipur

0.23

usta

0.23

 Recipes

0.23

æ°¸ä¸į

0.23

elu

0.23

 FAQs

0.23

Activations Density 0.001%

positive outcomes and living well

No Comments

No Known Activations