INDEX

Explanations

Asking for or giving opinions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åħ¶æ¬¡æĺ¯

-0.28

æĹłç©·

-0.27

')+

-0.26

èĻ¢

-0.25

æĸ¹ä½į

-0.24

Ð°Ð½Ð¸ÑĨ

-0.24

æĺİçŁ¥

-0.24

legg

-0.24

ç¯·

-0.23

éĺ

-0.23

POSITIVE LOGITS

 regularly

0.26

det

0.26

éľ²

0.25

-May

0.24

jun

0.24

bt

0.24

ç½²

0.24

Dra

0.24

rat

0.23

_det

0.23

Activations Density 3.730%

Asking for or giving opinions

No Comments

No Known Activations