© 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. 2397
    Prev
    Next
    INDEX
    Explanations

    say "互联网"

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

    No Comments

    Negative Logits
    (det
    -18.50
     Inc
    -16.88
     Mum
    -15.75
     reserv
    -15.63
    det
    -15.63
     Demon
    -15.56
     Pres
    -15.44
    示
    -15.38
    Det
    -15.25
    upil
    -15.25
    POSITIVE LOGITS
    注册
    21.38
    (utils
    21.13
     utils
    19.75
     app
    19.75
    Utils
    19.50
    utils
    18.75
    app
    18.63
    _registered
    18.50
    APP
    18.25
     Utils
    17.88
    Activations Density 0.036%

    No Known Activations