INDEX

Explanations

Code/software

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-native

-0.32

 native

-0.32

ä¸įä¿¡

-0.29

ä¸įçĶĺ

-0.29

 Native

-0.28

 indigenous

-0.27

çī©çĲĨ

-0.27

ä½Ļ

-0.26

phys

-0.26

Ĥ¹

-0.26

POSITIVE LOGITS

sie

0.27

å¼¼

0.27

å½ĸ

0.26

ä¾µçĬ¯

0.26

.Serve

0.25

åķĥ

0.25

éħĬ

0.24

è´£ä»»ç¼ĸè¾ĳ

0.24

(sorted

0.24

éĢĸ

0.24

Activations Density 0.011%

Code/software

No Comments

No Known Activations