© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 43755
    Prev
    Next
    INDEX
    Explanations

    virus, malware, security threats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æij¸çĿĢ
    -0.08
    juries
    -0.07
    онаÑĤ
    -0.07
    opaque
    -0.07
     instagram
    -0.06
    对äºİè¿Ļ个
    -0.06
    微信æī«çłģ
    -0.06
    è¢«ä¾ĽåºĶåķĨ
    -0.06
    ä»»ä½ķåªĴä½ĵ
    -0.06
     Pixar
    -0.06
    POSITIVE LOGITS
     virus
    0.12
     antivirus
    0.11
     malware
    0.11
    çĹħæ¯Ĵ
    0.11
     viruses
    0.10
     Virus
    0.09
     заÑĢа
    0.09
     quarantine
    0.09
    æľ¨é©¬
    0.09
    æ½ľä¼ı
    0.09
    Activations Density 0.158%

    No Known Activations