INDEX

Explanations

technical/medical documents

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

 uÃ§

-0.34

 discharged

-0.31

 discharge

-0.31

å¼ĥ

-0.30

æµģåĩº

-0.28

 outlet

-0.28

 expelled

-0.28

 deleted

-0.27

 discarded

-0.26

åĩºåİ»

-0.26

POSITIVE LOGITS

å¹²äºĭ

0.37

æŃ¢

0.28

 Alloc

0.26

ç§į

0.26

ysi

0.25

 Editors

0.25

æŃ£

0.25

 Travis

0.24

 Benchmark

0.24

Benchmark

0.24

Activations Density 0.001%

technical/medical documents

No Comments

No Known Activations