INDEX

Explanations

deposition

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 onto

-0.31

æ¸£

-0.28

åĽº

-0.28

illin

-0.27

åŀĥåľ¾

-0.27

äºĮ

-0.26

å¾Ģ

-0.25

wet

-0.25

è§ĦèĮĥ

-0.25

-wh

-0.24

POSITIVE LOGITS

Ð±Ð¾Ð¹

0.27

èĢģå¦Ī

0.27

kf

0.26

åĴ©

0.26

è¯°

0.26

_sector

0.25

é©ļ

0.25

createForm

0.24

 revelations

0.23

Sector

0.23

Activations Density 0.040%

deposition

No Comments

No Known Activations