INDEX

Explanations

Hun/un variations

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

lush

-0.28

Bloc

-0.26

GroupName

-0.25

 pumped

-0.25

æĬ¥åĪĬ

-0.24

å¸ĸåŃĲ

-0.24

-redux

-0.24

Publisher

-0.24

.observable

-0.23

 Beginner

-0.23

POSITIVE LOGITS

éĢīåıĸ

0.28

 fines

0.27

Fine

0.26

çĽ¸åħ³äººåĳĺ

0.26

çļĦåİŁåĪĻ

0.26

è§Ħå®ļçļĦ

0.25

ToObject

0.25

 fine

0.25

argo

0.25

orum

0.25

Activations Density 0.073%

Hun/un variations

No Comments

No Known Activations