INDEX

Explanations

web security vulnerabilities

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_12.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.12.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å®ļåĲĳ

-0.28

iana

-0.27

ockey

-0.27

ä¸īé¡¹

-0.26

ailable

-0.26

minster

-0.25

chein

-0.25

mdl

-0.25

esson

-0.24

å·´æĭī

-0.24

POSITIVE LOGITS

èµ¢å®¶

0.29

 StreamWriter

0.28

ant

0.27

ìł¤

0.26

ca

0.25

aller

0.25

ylation

0.25

è´£ä»»äºº

0.25

antan

0.24

intern

0.24

Activations Density 0.001%

web security vulnerabilities

No Comments

No Known Activations