© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1986
    Prev
    Next
    INDEX
    Explanations

    档案

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

    No Comments

    Negative Logits
     arch
    -45.25
     ARCH
    -42.00
     Arch
    -41.75
    ARCH
    -40.25
    arch
    -40.00
    Arch
    -40.00
    Archive
    -39.25
    /arch
    -39.00
    _arch
    -39.00
     archive
    -39.00
    POSITIVE LOGITS
     gender
    16.75
    サー
    16.75
    性别
    16.75
     comput
    16.63
    UIT
    16.38
    eya
    15.69
    _mu
    15.63
     Gender
    15.31
    电机
    15.25
    五金
    15.25
    Activations Density 0.065%

    No Known Activations