INDEX

Explanations

y

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

æ£Ĵ

-0.26

(TM

-0.26

fil

-0.26

 destin

-0.26

dif

-0.26

iful

-0.25

fou

-0.25

cf

-0.24

Cd

-0.24

 filled

-0.24

POSITIVE LOGITS

å£°

0.29

ocracy

0.28

ç²²

0.26

ivet

0.26

å§Ķåĳĺä¼ļ

0.25

åŀ¢

0.25

æĸ¹ãģ¯

0.25

èģ²

0.25

çĵ®

0.24

 morally

0.24

Activations Density 0.002%

y

No Comments

No Known Activations