INDEX

Explanations

code, programming

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

å¾Ģä¸Ĭ

-0.32

ç®Ń

-0.27

 Gone

-0.27

ÑħÐ¾Ð¶

-0.27

å¦«

-0.26

æĮĩåįĹ

-0.26

åĲĪçĲĨæĢ§

-0.25

 sibling

-0.25

åıĹéĻĲ

-0.25

æĢ§åĴĮ

-0.25

POSITIVE LOGITS

adv

0.30

noun

0.27

 machines

0.27

ButtonType

0.27

äºĺ

0.26

 machinery

0.26

ptime

0.25

æ°¸ä¸į

0.24

ãĥĥãĥĦ

0.24

è¯°

0.24

Activations Density 0.012%

code, programming

No Comments

No Known Activations