INDEX

Explanations

Assuring Rigor/Quality/Safety

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Mag

-0.26

 tÅĤum

-0.25

gings

-0.25

Mag

-0.24

ç¤¾ä¼ļåĮĸ

-0.24

ç»

-0.24

Å±

-0.24

åĬ¬

-0.24

ger

-0.23

 radios

-0.23

POSITIVE LOGITS

apore

0.32

agnostics

0.28

æ·»åĬłåīĤ

0.26

Ð°Ð¹Ð½

0.26

stance

0.26

npj

0.26

åĬ²

0.26

nty

0.26

SpaceItem

0.25

ogra

0.25

Activations Density 0.040%

Assuring Rigor/Quality/Safety

No Comments

No Known Activations