INDEX

Explanations

scientific and legal texts

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

åĩŃ

-0.32

 Serious

-0.27

Mat

-0.27

orean

-0.26

fieldset

-0.26

åĲ¬

-0.25

åĲ¬å¾Ĺ

-0.25

Mat

-0.25

(Mat

-0.25

ì§¸

-0.24

POSITIVE LOGITS

èĥĨ

0.28

aal

0.27

åĮĹæŀģ

0.27

 reversed

0.26

 interiors

0.26

BoxLayout

0.25

otch

0.25

ãĤ¢ãĥĬ

0.25

 capacit

0.25

 bile

0.24

Activations Density 0.013%

scientific and legal texts

No Comments

No Known Activations