INDEX

Explanations

wellbeing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵

-0.07

amazon

-0.07

ROWN

-0.07

 loader

-0.06

Guide

-0.06

Magento

-0.06

LOUD

-0.06

 addTarget

-0.06

TextNode

-0.06

ass

-0.06

POSITIVE LOGITS

.SerializedName

0.08

-being

0.07

典型

0.07

偏差

0.07

leh

0.07

 Strings

0.06

慷

0.06

etag

0.06

就會

0.06

rief

0.06

Activations Density 0.008%

wellbeing

No Comments

No Known Activations