INDEX

Explanations

Operating systems and MOS transistors

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

æµħ

-0.27

affe

-0.26

æŃ¤ç±»

-0.26

fest

-0.26

æĳ©

-0.24

 technically

-0.24

ÑĤÐ²ÐµÑĢ

-0.24

 easiest

-0.24

imoto

-0.23

ä¼¢

-0.23

POSITIVE LOGITS

axy

0.27

nip

0.27

acht

0.26

axes

0.25

.raise

0.25

lymp

0.24

PEG

0.24

çģµæĦŁ

0.24

essages

0.24

 StringWriter

0.23

Activations Density 0.034%

Operating systems and MOS transistors

No Comments

No Known Activations