INDEX

Explanations

Human anatomy

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

æĻ¨

-0.29

ulers

-0.28

eu

-0.28

eled

-0.28

enn

-0.27

éĢļçĶ¨

-0.27

iset

-0.26

acco

-0.26

 Happ

-0.25

Ð»Ð°Ð´

-0.25

POSITIVE LOGITS

 descon

0.27

ç½¹

0.26

 solitude

0.25

æľīéĹ®é¢ĺ

0.25

sod

0.25

 infections

0.25

 anomalies

0.24

War

0.24

 vacancies

0.24

Tw

0.23

Activations Density 0.028%

Human anatomy

No Comments

No Known Activations