INDEX

Explanations

Security vulnerabilities

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èĹ»

-0.28

éķĢ

-0.27

ç¥ł

-0.27

ç°ª

-0.26

ÙĬØŃ

-0.26

ä¸ĺ

-0.25

plet

-0.25

àµ»

-0.25

æĿ¾å¼Ľ

-0.24

 overd

-0.24

POSITIVE LOGITS

æĶ»åĩ»

0.50

 vulnerabilities

0.49

 vulnerability

0.48

æģ¶æĦı

0.44

æ¼ıæ´ŀ

0.44

 vulner

0.43

 malicious

0.43

 attacker

0.42

 attackers

0.42

CVE

0.41

Activations Density 1.858%

Security vulnerabilities

No Comments

No Known Activations