INDEX

Explanations

acronyms/abbreviations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ason

-0.26

Macro

-0.25

 confusing

-0.24

_MACRO

-0.24

Ø§Øº

-0.24

 soak

-0.24

utter

-0.23

air

-0.23

 soaking

-0.23

prep

-0.23

POSITIVE LOGITS

å¹¶åĲĳ

0.36

å¹¶åľ¨

0.28

ERY

0.27

å¹¶

0.26

æ¡Ĩ

0.26

fav

0.26

å¹¶å°Ĩ

0.25

tv

0.25

elerik

0.25

å¹¶äºİ

0.24

Activations Density 0.002%

acronyms/abbreviations

No Comments

No Known Activations