INDEX

Explanations

image/data analysis, windowing

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

arded

-0.28

äº§ä¸ļ

-0.27

æĪ´çĿĢ

-0.27

æĸĩåĮĸäº§ä¸ļ

-0.25

 Canter

-0.25

è¿Ļåĩł

-0.25

á»Ļ

-0.25

è§Ĥå¿µ

-0.25

_"+

-0.24

 sciences

-0.24

POSITIVE LOGITS

 pack

0.32

-package

0.29

pack

0.27

plate

0.27

system

0.27

åĮħè£ħ

0.27

éģĵ

0.27

çĹ

0.26

-pack

0.26

æį

0.26

Activations Density 0.009%

image/data analysis, windowing

No Comments

No Known Activations