INDEX

Explanations

scientific and technical writing

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

ç¯ĩ

-0.31

èĬĤ

-0.30

åºĶçĶ¨

-0.30

äºĭå®ŀ

-0.28

 fact

-0.27

 application

-0.27

çİ°å®ŀ

-0.27

åĳĺ

-0.27

 facts

-0.26

 downstream

-0.26

POSITIVE LOGITS

SError

0.25

ampa

0.25

çļĦæĪĲæľ¬

0.24

Pocket

0.24

æİı

0.24

èħ®

0.24

ItemClickListener

0.24

çĽ®åīįå·²ç»ı

0.24

.promise

0.23

 Serg

0.23

Activations Density 0.036%

scientific and technical writing

No Comments

No Known Activations