INDEX

Explanations

yrs

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

NotFoundError

-0.30

 deal

-0.28

annotate

-0.27

 bowel

-0.25

çī¹æĸ¯

-0.25

 Deal

-0.25

æĻĸ

-0.25

ential

-0.24

ä¹ĺ

-0.24

elper

-0.23

POSITIVE LOGITS

 meaning

0.25

aks

0.24

ä¸¤ä¸ªæľĪ

0.23

å°±æľī

0.23

/close

0.23

ä¾¬

0.23

illions

0.23

meaning

0.23

oat

0.23

è¯¥åİ¿

0.23

Activations Density 7.006%

yrs

No Comments

No Known Activations