INDEX

Explanations

nose

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

å¯Ĩ

-0.26

èµ«

-0.25

ç£Ĳ

-0.25

åĻ©

-0.25

ç«ĭåį³

-0.25

ç³»

-0.25

cono

-0.24

 commands

-0.24

Ä±kl

-0.24

çĽĺ

-0.24

POSITIVE LOGITS

STALL

0.31

è§Ĵ

0.29

è§Ĵåº¦

0.29

éĽªèĬ±

0.28

emme

0.27

 folks

0.27

.Angle

0.27

æ¯ıä¸ªäºº

0.25

äººäºº

0.25

-angle

0.25

Activations Density 0.003%

nose

No Comments

No Known Activations