INDEX

Explanations

to

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

æĺ¨æĻļ

-0.28

 unpredict

-0.27

 unpredictable

-0.26

 Stokes

-0.26

DX

-0.26

Gy

-0.25

å¼ĢæĶ¾å¼ı

-0.25

 ÙħÙĪØ§

-0.24

çµĲ

-0.24

çī©çĲĨåŃ¦

-0.24

POSITIVE LOGITS

 invasive

0.30

obili

0.28

zoek

0.28

.pem

0.27

PointerType

0.26

 invasion

0.25

erie

0.25

 contrario

0.25

ey

0.25

bih

0.25

Activations Density 0.007%

to

No Comments

No Known Activations