© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15227
    Prev
    Next
    INDEX
    Explanations

    say 年

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

    No Comments

    Negative Logits
    >v
    -16.25
    tsy
    -15.69
    acific
    -15.56
    自愿
    -14.88
    nation
    -14.50
    -v
    -14.50
    PURE
    -14.31
    /rfc
    -14.31
     Virgin
    -14.25
     Volley
    -14.25
    POSITIVE LOGITS
     Dub
    17.63
     claw
    17.25
    car
    17.13
    橹
    17.00
     Kad
    17.00
    ija
    17.00
     Drum
    17.00
    滩
    16.75
     Car
    16.38
    桀
    16.38
    Activations Density 0.647%

    No Known Activations