INDEX

Explanations

physical

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

 physical

-0.27

 physicists

-0.27

çī©çĲĨ

-0.26

 váºŃt

-0.26

 Density

-0.25

ighton

-0.25

Physical

-0.25

 Physical

-0.24

pecially

-0.24

å¥½çļĦ

-0.24

POSITIVE LOGITS

 Singleton

0.28

Disposable

0.25

isd

0.25

FromClass

0.25

ras

0.24

bish

0.24

à¹īà¸ĩ

0.24

 flats

0.23

æĸĩæĺĮ

0.23

nger

0.23

Activations Density 0.998%

physical

No Comments

No Known Activations