© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1238
    Prev
    Next
    INDEX
    Explanations

    [Eu] => [Euclid]

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

    No Comments

    Negative Logits
    Mus
    -27.50
    MU
    -25.75
    mus
    -25.13
     Muse
    -23.63
     muse
    -23.50
     MU
    -23.13
    ミュ
    -22.75
     mu
    -22.63
     Mus
    -22.63
     muscle
    -21.88
    POSITIVE LOGITS
    ông
    16.88
    /api
    15.63
    _api
    15.50
     api
    15.44
    api
    15.25
    .api
    14.81
    Carbon
    14.63
    设计
    14.63
    ikers
    14.56
     city
    14.38
    Activations Density 0.367%

    No Known Activations