INDEX

Explanations

this

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

èĥĨ

-0.26

èĨ½

-0.26

ä»Ģä¹Īåĳ¢

-0.25

æ¡¥

-0.25

æ¸£

-0.25

ä¸ºèĩªå·±

-0.24

oldt

-0.24

ç½²

-0.24

 ÐĲÐ²ÑĤÐ¾ÑĢ

-0.24

ĮĢ

-0.23

POSITIVE LOGITS

éĨī

0.26

çĿ¡

0.26

yes

0.24

jang

0.24

eve

0.24

 shape

0.24

æ»ĭåħ»

0.23

Ø¯ÙĪÙĨ

0.23

yes

0.23

èī²æ³½

0.23

Activations Density 0.233%

this

No Comments

No Known Activations