INDEX

Explanations

Academic and writing contexts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nings

-0.27

æľĢåĲİä¸Ģä¸ª

-0.26

æĤ¬

-0.26

Ĥ¬

-0.26

ech

-0.24

éļ±

-0.24

iot

-0.23

åı£å¤´

-0.23

scheme

-0.23

nick

-0.23

POSITIVE LOGITS

ADED

0.34

åħ¶ä»ĸäºº

0.29

 collaborators

0.26

æĮŀ

0.25

enne

0.25

æĶ¹èī¯

0.25

pty

0.25

 protector

0.25

ä¸įæħİ

0.25

æ°´éĿ¢

0.24

Activations Density 0.057%

Academic and writing contexts

No Comments

No Known Activations