INDEX

Explanations

ing

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

opyright

-0.27

 Markup

-0.26

éªı

-0.25

 transports

-0.24

å¹´æĬ¥

-0.24

 transport

-0.24

flation

-0.24

 uplift

-0.23

 transporting

-0.23

 ripe

-0.23

POSITIVE LOGITS

Ä±cÄ±

0.30

è¸½

0.28

ä¹łæĥ¯äºĨ

0.27

æĢª

0.27

CHAPTER

0.26

ä¹łæĥ¯

0.25

ç´łé£Ł

0.25

rete

0.24

æĥ¯

0.24

hab

0.24

Activations Density 0.020%

ing

No Comments

No Known Activations