INDEX

Explanations

architecture and design

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

QUI

-0.33

OfYear

-0.29

 traceback

-0.29

 exchange

-0.28

 coverage

-0.26

 Shib

-0.25

 cover

-0.25

 actual

-0.25

 dioxide

-0.25

åŃĲéĩĮ

-0.25

POSITIVE LOGITS

vince

0.28

Ã«r

0.27

orde

0.27

ahkan

0.26

 lenses

0.26

inces

0.26

 respectfully

0.25

 nextProps

0.25

RSpec

0.24

iek

0.24

Activations Density 0.018%

architecture and design

No Comments

No Known Activations