INDEX

Explanations

code

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

ÑĢÑĥÐ´

-0.29

éĢļæĬ¥

-0.28

 critically

-0.27

 stdClass

-0.26

 Corn

-0.25

æıĴ

-0.25

æ¡´

-0.25

eson

-0.25

uÃ©

-0.25

é£İéĽ¨

-0.24

POSITIVE LOGITS

éĺħ

0.30

afs

0.26

DLC

0.26

arus

0.26

Mog

0.25

fur

0.25

(interval

0.25

 scram

0.25

 Browns

0.24

(dm

0.24

Activations Density 0.015%

code

No Comments

No Known Activations