INDEX

Explanations

Latin

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

 acomp

-0.27

 MessageType

-0.26

 packed

-0.26

(pack

-0.26

ypse

-0.26

 UserType

-0.25

idl

-0.25

atem

-0.25

OCT

-0.24

ican

-0.24

POSITIVE LOGITS

ä¸ĢåľĪ

0.31

Ã¼m

0.29

 Labs

0.26

ç¿ĺ

0.25

.ArgumentParser

0.25

body

0.25

é¾Ħ

0.25

ä»¿

0.25

åķĨ

0.24

è§ŀ

0.24

Activations Density 0.025%

Latin

No Comments

No Known Activations