INDEX

Explanations

Gibberish-like text

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

Sac

-0.28

(Locale

-0.25

Priority

-0.25

FY

-0.25

æĪ·

-0.24

Ð¿Ð°Ñģ

-0.24

errat

-0.24

alic

-0.24

ric

-0.24

rys

-0.23

POSITIVE LOGITS

 aiding

0.26

à¸·à¸Ńà¸Ļ

0.26

fullname

0.26

æīĢæīĢ

0.25

ounder

0.25

æ°´éĿ¢

0.25

éľ²å¤©

0.24

 fullname

0.24

mak

0.24

uchar

0.24

Activations Density 20.563%

Gibberish-like text

No Comments

No Known Activations