INDEX

Explanations

code and technical writing

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¥Ī

-0.29

éĺµ

-0.28

ony

-0.27

urn

-0.27

yster

-0.27

ooky

-0.26

ty

-0.26

ouse

-0.25

FileSync

-0.25

amb

-0.24

POSITIVE LOGITS

æĤ¨çļĦ

0.26

é²ĭ

0.26

etration

0.24

lei

0.24

pll

0.24

itizer

0.24

 veniam

0.24

 baskets

0.23

Lit

0.23

PLL

0.23

Activations Density 0.018%

code and technical writing

No Comments

No Known Activations