INDEX

Explanations

code/mathematical notation

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

èĬ±æł·

-0.26

 Äĳá»©ng

-0.25

åĨľä¸ļå¤§åŃ¦

-0.25

fig

-0.25

 impres

-0.25

ious

-0.24

Ø

-0.23

unal

-0.23

 Muss

-0.23

 segregated

-0.23

POSITIVE LOGITS

èĮĥåĽ´

0.29

åĮºéĹ´

0.29

Interval

0.27

 range

0.27

 Range

0.27

 kaps

0.26

lopen

0.26

 setInterval

0.26

æĳĦ

0.25

edis

0.25

Activations Density 0.031%

code/mathematical notation

No Comments

No Known Activations