© 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. 13973
    Prev
    Next
    INDEX
    Explanations

    class

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

    No Comments

    Negative Logits
    unik
    -15.44
    圣地
    -15.38
    ighthouse
    -15.38
    产出
    -14.94
    iddleware
    -14.81
    产业链
    -14.75
     developer
    -14.63
    digest
    -14.31
     Templ
    -14.31
    _PROD
    -14.13
    POSITIVE LOGITS
     classes
    50.25
    班级
    47.50
     class
    47.25
     Classes
    45.50
    classes
    44.25
    Classes
    44.25
     Class
    43.75
    班
    43.50
    class
    43.00
     classe
    42.25
    Activations Density 0.724%

    No Known Activations