INDEX

Explanations

allow/enable

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

![

-0.28

undy

-0.27

UIS

-0.26

![

-0.26

CID

-0.26

èĢĮå·²

-0.25

[](

-0.25

gil

-0.25

 newRow

-0.25

lab

-0.24

POSITIVE LOGITS

vature

0.25

éĿ¢è²Į

0.24

ErrorException

0.24

"--

0.24

å¨ĺ

0.24

aller

0.23

Extent

0.23

(console

0.23

ppo

0.23

 rapid

0.23

Activations Density 0.025%

allow/enable

No Known Activations