INDEX

Explanations

sentenced

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

 humane

-0.08

 Bayesian

-0.08

 upheld

-0.08

 dusk

-0.07

gnore

-0.07

:k

-0.07

얗

-0.07

锬

-0.07

-school

-0.07

 DATABASE

-0.06

POSITIVE LOGITS

$/,

0.08

")[

0.07

🚚

0.07

################################

0.07

 StringBuilder

0.07

狐

0.07

が高い

0.07

قتل

0.07

methodName

0.07

🤩

0.07

Activations Density 0.003%

sentenced

No Comments

No Known Activations