INDEX

Explanations

common pronouns and "to be"

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

aged

-0.27

 Times

-0.27

Times

-0.26

cop

-0.26

 effort

-0.25

æįĨ

-0.25

æĬĬæīĭ

-0.24

 Club

-0.23

CRE

-0.23

é©¹

-0.23

POSITIVE LOGITS

éº¾

0.33

åĭ¤åĬ³

0.28

stress

0.26

usterity

0.26

/private

0.26

æĸ¹å¼ıè¿Ľè¡Į

0.26

fasta

0.25

äºĨèĩªå·±çļĦ

0.25

èĩªå·±çļĦ

0.24

OWN

0.24

Activations Density 0.003%

common pronouns and "to be"

No Comments

No Known Activations