INDEX

Explanations

Mount

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

ORED

-0.31

 spam

-0.30

 compound

-0.26

æīĵäºĨ

-0.25

çĿ¥

-0.24

éķ¶

-0.24

 nÃºi

-0.24

å¯¹å¾ħ

-0.24

çŁ³çģ°

-0.24

mount

-0.23

POSITIVE LOGITS

ä¸ĢåľĪ

0.29

cards

0.26

Ð»Ð¸ÑģÑĮ

0.25

 `;↵

0.24

kÃ¶p

0.24

ç£ĭåķĨ

0.23

sus

0.23

è§Ĵ

0.23

ledged

0.23

æĦŁçŁ¥

0.23

Activations Density 0.313%

Mount

No Comments

No Known Activations