INDEX

Explanations

disclaimers and code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

çİĭåŃĲ

-0.28

.intent

-0.26

reek

-0.26

åīĸ

-0.26

inidad

-0.25

äº¤åıī

-0.25

leness

-0.25

Ã¢t

-0.25

 ters

-0.25

 Cros

-0.24

POSITIVE LOGITS

 includes

0.39

 Include

0.38

 include

0.36

 Includes

0.36

includes

0.33

æ¶µçĽĸ

0.33

 inclusive

0.33

åĮħåĲ«

0.32

include

0.32

inclusive

0.31

Activations Density 0.003%

disclaimers and code

No Comments

No Known Activations