INDEX

Explanations

the

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

Selectors

-0.29

 gearing

-0.25

å¸ħ

-0.25

selectors

-0.25

 setSearch

-0.24

 spit

-0.24

EFR

-0.24

IQ

-0.24

 GOOD

-0.24

Implicit

-0.24

POSITIVE LOGITS

orea

0.32

ä¸ĢåĪ»

0.26

å¼¹

0.25

é¸©

0.25

.launch

0.25

éĿ¢åīį

0.24

ious

0.24

ãģ¾ãģļ

0.24

éĢĨè¢Ń

0.24

æį

0.23

Activations Density 0.013%

the

No Comments

No Known Activations