INDEX

Explanations

fluoroscopic imaging Method: 1, all max activating tokens have to do with fluor

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Uph

-0.07

SEA

-0.07

自主创新

-0.07

迅猛

-0.07

 Steele

-0.07

六个月

-0.07

方方面面

-0.07

imageView

-0.07

 outing

-0.07

发展壮大

-0.07

POSITIVE LOGITS

 rút

0.07

.cd

0.07

 acces

0.07

 количество

0.07

嵖

0.07

awa

0.07

 intrig

0.07

velle

0.07

ecret

0.07

once

0.06

Activations Density 0.006%

fluoroscopic imaging Method: 1, all max activating tokens have to do with fluor

No Comments

No Known Activations

fluoroscopic imaging Method: 1, all max activating tokens have to do with fluor

No Comments

No Known Activations