INDEX

Explanations

politics, conflicts, science

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

è§¦åıĳ

-0.28

ButtonDown

-0.28

çĶµè´¹

-0.28

çĽĳæĬ¤

-0.27

ä¿¯

-0.27

ä¾¿äºİ

-0.26

ä¸īäºº

-0.25

å¿ĥçĲĨåŃ¦

-0.24

 Datensch

-0.24

æľīåĬ©

-0.24

POSITIVE LOGITS

æ¸¸

0.28

(cache

0.26

æĭ¦

0.26

éĩĩ

0.25

Naming

0.25

loc

0.25

 Ð¿ÐµÑĢÐ²ÑĥÑİ

0.24

ç¥ī

0.24

Ð¸Ð½ÑĤÐµÑĢ

0.24

imb

0.24

Activations Density 0.016%

politics, conflicts, science

No Comments

No Known Activations