INDEX

Explanations

ethical

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

ailles

-0.30

edium

-0.29

ernity

-0.28

WebHost

-0.28

osos

-0.26

lesc

-0.26

shr

-0.26

ilarity

-0.25

lobals

-0.25

taire

-0.25

POSITIVE LOGITS

æ£¹

0.28

moment

0.28

yet

0.27

è²»

0.27

lo

0.26

ãĤģ

0.26

bon

0.25

ibi

0.25

elo

0.24

 moment

0.24

Activations Density 0.008%

ethical

No Comments

No Known Activations