INDEX

Explanations

University

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

ä¸įè§£

-0.30

-fit

-0.28

pton

-0.27

acute

-0.26

lu

-0.26

 indefinitely

-0.26

ä¸Ģè½®

-0.25

ä¸Ģæ®µ

-0.25

ç§į

-0.25

ä¹ĥ

-0.25

POSITIVE LOGITS

 ÑģÑĤÐ°Ð»Ð¾

0.28

sources

0.26

 Marble

0.26

Turkey

0.26

à¸ªà¸¡à¸²

0.25

âĨĺ

0.25

pig

0.24

 concentration

0.23

æ³±

0.23

 sources

0.23

Activations Density 0.030%

University

No Comments

No Known Activations