INDEX

Explanations

news, events, updates

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çļĦæł¹æľ¬

-0.28

PIP

-0.27

åĴĮå°ļ

-0.27

-Headers

-0.26

åķĸ

-0.26

æł¹æºĲ

-0.25

pek

-0.25

 slee

-0.25

å¥½çľĭçļĦ

-0.25

 bibliography

-0.24

POSITIVE LOGITS

(reverse

0.32

essim

0.29

 social

0.29

ught

0.27

social

0.27

guarded

0.27

 poses

0.27

eh

0.27

 about

0.27

ato

0.26

Activations Density 0.954%

news, events, updates

No Comments

No Known Activations