© 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. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14395
    Prev
    Next
    INDEX
    Explanations

    say ">"

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

    No Comments

    Negative Logits
    porter
    -18.38
    _COMPONENT
    -18.00
     Hercules
    -16.63
    炀
    -16.00
    midi
    -15.88
    мес
    -15.75
     Porto
    -15.69
    igators
    -15.69
    arms
    -15.63
    ardo
    -15.63
    POSITIVE LOGITS
    标题
    17.38
    分析
    14.94
     motion
    14.69
    扫描
    14.31
    事件
    14.31
    ouns
    14.19
    错
    14.13
    运动
    13.88
     analys
    13.81
    肖
    13.50
    Activations Density 0.056%

    No Known Activations