INDEX

Explanations

Federal

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

nore

-0.28

è®²å¸Ī

-0.27

è´¢

-0.27

observable

-0.25

dap

-0.25

ayout

-0.24

 darf

-0.24

å¥´

-0.24

 Experts

-0.23

äºĶåĪĨéĴŁ

-0.23

POSITIVE LOGITS

å¹´ç¬¬

0.28

anan

0.28

éĢļåħ³

0.25

tÃ¼r

0.25

 thickness

0.24

æ½¦

0.24

oit

0.24

Thickness

0.24

åľ°æ¯¯

0.24

ecd

0.23

Activations Density 0.002%

Federal

No Known Activations