INDEX

Explanations

Numbers and technical reports

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

noinspection

-0.28

 territory

-0.28

puter

-0.27

ä¼ĳ

-0.26

 territories

-0.25

 deposited

-0.25

nic

-0.25

 dice

-0.24

 Territories

-0.24

 starters

-0.23

POSITIVE LOGITS

ä¸İæĹ¶

0.30

APS

0.28

éĢģåĩº

0.27

ROT

0.26

reon

0.25

visibility

0.25

 Passage

0.24

idents

0.24

ILLE

0.24

prs

0.24

Activations Density 0.003%

Numbers and technical reports

No Comments

No Known Activations