INDEX

Explanations

No Explanations Found

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

Dim

-0.08

.Safe

-0.06

ลำ

-0.06

מסוגל

-0.06

ampoline

-0.06

.userName

-0.06

ᐢ

-0.06

vô

-0.06

 Desc

-0.06

 Batman

-0.06

POSITIVE LOGITS

𬭬

0.08

禚

0.08

 communal

0.08

�

0.07

雕刻

0.07

 ************************

0.07

 seçim

0.07

镂

0.07

コレ

0.07

 конкурс

0.07

Activations Density 0.001%

No Comments

No Known Activations