INDEX

Explanations

to

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rub

-0.29

tee

-0.29

çĽ®

-0.27

 má»¥c

-0.27

åģļ

-0.26

jee

-0.26

åĲĪä½ľ

-0.25

æĻķ

-0.24

æī¾åĪ°

-0.24

å¾ĹåĪ°

-0.24

POSITIVE LOGITS

ÑĨÐ¾Ð²

0.29

ä»ħä»£è¡¨

0.27

ullo

0.27

_utilities

0.26

ichten

0.26

invert

0.25

UiThread

0.25

éĤ£ä¹Īå®¹æĺĵ

0.24

AppComponent

0.24

ä¸¾æĬ¥çĶµè¯Ŀ

0.24

Activations Density 0.053%

to

No Comments

No Known Activations