INDEX

Explanations

each

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 contrario

-0.30

.setPrototypeOf

-0.27

èº¬

-0.26

atchet

-0.26

è·ĭ

-0.24

çºªå¾ĭ

-0.24

="--

-0.23

è´¹

-0.23

ä¸Ģä¸ĸ

-0.23

 WebDriverWait

-0.23

POSITIVE LOGITS

oints

0.29

ä¸Ģç«Ļ

0.28

ear

0.27

postData

0.25

ä½ĵéªĮ

0.24

alary

0.24

åľ¨æĪĳçļĦ

0.24

/shop

0.23

mars

0.23

 tall

0.23

Activations Density 0.002%

each

No Comments

No Known Activations