INDEX

Explanations

administrative locations

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

åĭº

-0.30

lat

-0.28

æ¨ª

-0.27

åĮ¡

-0.27

/@

-0.26

(shared

-0.26

SSR

-0.26

occupation

-0.25

 occupation

-0.25

 share

-0.25

POSITIVE LOGITS

ervo

0.29

æ¢Ĺ

0.27

ycl

0.26

åīĮ

0.26

éĶĢ

0.25

ardi

0.25

ToObject

0.24

evt

0.24

anel

0.24

CIT

0.24

Activations Density 0.012%

administrative locations

No Comments

No Known Activations