INDEX

Explanations

numbers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 minor

-0.26

æ¬¡

-0.26

çĸĳ

-0.25

-Owned

-0.25

-stars

-0.24

å¤ĩ

-0.24

å¼Ĥè®®

-0.24

opies

-0.24

å£°éģĵ

-0.24

éĩįå¤§

-0.24

POSITIVE LOGITS

ContentSize

0.28

é£§

0.27

 emphasized

0.27

æµ£

0.26

ienie

0.26

ç²ī

0.25

éĽ·æĸ¯

0.25

itel

0.24

pow

0.24

 capsules

0.23

Activations Density 0.004%

numbers

No Comments

No Known Activations