INDEX

Explanations

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

 bell

-0.28

oriented

-0.28

 Shell

-0.27

 stars

-0.26

ac

-0.26

 star

-0.25

 sensor

-0.25

ensor

-0.25

 oriented

-0.25

 shell

-0.24

POSITIVE LOGITS

 categoryName

0.30

 getCategory

0.28

åľ°åĮº

0.27

regions

0.26

 rÃ©gion

0.26

è¢«æĬĵ

0.26

åľ°åĮºçļĦ

0.25

åľ°åįĢ

0.25

leck

0.25

ANNEL

0.25

Activations Density 0.193%

programming

No Comments

No Known Activations