INDEX

Explanations

update

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

åĪĬ

-0.28

erge

-0.27

àª³

-0.26

ISS

-0.25

åĪ°åºķ

-0.25

inte

-0.25

éª¨

-0.25

issen

-0.24

uco

-0.23

plit

-0.23

POSITIVE LOGITS

 lives

0.26

arts

0.26

Brains

0.25

æĺ¯æľī

0.24

 dramatic

0.24

GSM

0.24

.FromSeconds

0.24

 Supplier

0.23

.Dom

0.23

bearing

0.23

Activations Density 0.047%

update

No Comments

No Known Activations