INDEX

Explanations

Code, recipes, questions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 TextArea

-0.26

mpeg

-0.25

å¼ĢæĿ¥

-0.25

éĺĦ

-0.25

cal

-0.25

 Valent

-0.24

++++++++++++++++++++++++++++++++

-0.24

 wooden

-0.24

=username

-0.24

","",

-0.24

POSITIVE LOGITS

SenderId

0.30

 misrepresented

0.27

osl

0.26

descending

0.25

æĢ¥

0.25

__).

0.24

/master

0.24

æīįèĥ½

0.24

slashes

0.24

 drip

0.23

Activations Density 0.000%

Code, recipes, questions

No Comments

No Known Activations