INDEX

Explanations

Germany

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èĥĮåĮħ

-0.29

-exp

-0.27

æ¸´æľĽ

-0.26

.esp

-0.25

Peb

-0.25

 appart

-0.24

Authorities

-0.24

ismo

-0.23

åı¤åŁİ

-0.23

 Islands

-0.23

POSITIVE LOGITS

amon

0.29

rophy

0.25

memberOf

0.25

PROTO

0.25

plain

0.25

åĨ·

0.24

ModelState

0.24

ä¼ļéķ¿

0.24

wit

0.24

onian

0.24

Activations Density 0.005%

Germany

No Comments

No Known Activations