INDEX

Explanations

eager

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

/posts

-0.27

äºŃ

-0.27

 Clown

-0.25

UV

-0.25

æĸĩç«łæĿ¥æºĲ

-0.24

 urlString

-0.24

åİŁæĸĩ

-0.23

_uv

-0.23

 crane

-0.23

erman

-0.23

POSITIVE LOGITS

ongan

0.29

prit

0.28

 cropping

0.26

ewe

0.24

ãĥ¬ãĤ¹

0.24

çĲĨå·¥å¤§åŃ¦

0.24

é©·

0.24

{}",

0.24

thro

0.24

_SAFE

0.23

Activations Density 52.425%

eager

No Comments

No Known Activations