© 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. 14763
    Prev
    Next
    INDEX
    Explanations

    French Enlightenment ideas

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

    No Comments

    Negative Logits
    追踪
    -16.50
     MVC
    -16.38
     Track
    -16.25
    trä
    -16.25
    综合整治
    -16.13
    跟踪
    -15.88
    стрел
    -15.81
     Motorcycle
    -15.69
     tracked
    -15.38
    üzü
    -15.31
    POSITIVE LOGITS
     Enlightenment
    20.25
    COPE
    16.13
    iode
    15.88
    公子
    15.75
    發表
    14.94
    úb
    14.94
     Vol
    14.94
    쇄
    14.81
     Mens
    14.63
    送去
    14.63
    Activations Density 0.343%

    No Known Activations