INDEX

Explanations

informed

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

¾ç¤º

-0.29

xAA

-0.29

bstract

-0.28

stract

-0.26

mon

-0.25

anax

-0.25

:numel

-0.25

APE

-0.25

deer

-0.25

çĽĳäºĭ

-0.24

POSITIVE LOGITS

æµŀ

0.33

Ð·Ð¾Ð²

0.26

.allocate

0.26

å±Ĭ

0.26

 trom

0.25

 Fram

0.25

conversion

0.25

æĬ±çĿĢ

0.24

jp

0.24

åĨ·åį´

0.23

Activations Density 2.174%

informed

No Comments

No Known Activations