© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15424
    Prev
    Next
    INDEX
    Explanations

    say affairs

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BaseModel
    -16.25
     Helvetica
    -16.00
    偏
    -15.81
     Desmond
    -15.63
    есс
    -15.25
    橋
    -15.06
    创新
    -14.88
    符号
    -14.75
    品牌
    -14.75
    brands
    -14.69
    POSITIVE LOGITS
    事务
    27.38
    行政
    24.13
     administrative
    23.50
    政务
    22.63
     admin
    21.13
     Admin
    20.75
    admin
    20.38
    Admin
    20.00
     Affairs
    19.63
     admins
    19.50
    Activations Density 0.351%

    No Known Activations