INDEX

Explanations

methods, systems, processes

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

umed

-0.26

PJ

-0.25

ä¹ĸ

-0.25

èļ¯

-0.24

å¤§å·´

-0.24

 Booker

-0.24

æĸ½èĤ¥

-0.24

åºķå±Ĥ

-0.24

 Territories

-0.24

cobra

-0.24

POSITIVE LOGITS

æķ¢

0.28

moth

0.27

 orally

0.27

åĲĪ

0.27

ivor

0.27

iring

0.27

 hosts

0.26

ãĤįãģĨ

0.26

 garg

0.26

hosts

0.26

Activations Density 0.011%

methods, systems, processes

No Comments

No Known Activations