INDEX

Explanations

0

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.future

-0.28

CC

-0.26

ä¹Łæĺ¯ä¸Ģä¸ª

-0.25

èĴĻ

-0.24

æĦ¿

-0.23

 Franco

-0.23

æľªæĿ¥

-0.23

çº§ä»¥ä¸Ĭ

-0.23

CC

-0.23

 Viewer

-0.23

POSITIVE LOGITS

ANCE

0.28

erer

0.26

antee

0.26

onte

0.25

iginal

0.25

Ã´m

0.25

ãĤ¿ãĥ³

0.24

 dÃ¼ÅŁÃ¼k

0.24

igner

0.24

iments

0.24

Activations Density 0.001%

0

No Comments

No Known Activations