© 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. 2171
    Prev
    Next
    INDEX
    Explanations

    乡村

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

    No Comments

    Negative Logits
    ennen
    -18.38
    volt
    -17.38
     det
    -17.00
    _det
    -15.25
    det
    -15.13
     gen
    -14.81
    Perm
    -14.75
     Perm
    -14.63
    getInt
    -14.31
    定
    -14.19
    POSITIVE LOGITS
    乡村
    39.75
    注册
    24.13
    (ctx
    23.63
    .ctx
    23.25
     ctx
    23.00
    乙方
    21.63
    (visitor
    21.38
    [idx
    21.13
     Visitor
    20.75
    Ctx
    20.63
    Activations Density 0.039%

    No Known Activations