© 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. 2384
    Prev
    Next
    INDEX
    Explanations

    say "Kur"

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

    No Comments

    Negative Logits
     cap
    -20.50
    cap
    -20.38
    det
    -20.25
    Fac
    -19.88
     Cap
    -19.38
     caps
    -19.00
     rec
    -18.38
    ,args
    -18.00
    fac
    -17.50
    Cap
    -17.38
    POSITIVE LOGITS
     Kur
    63.75
     cur
    55.75
    Cur
    54.00
    (cur
    54.00
     kur
    52.75
    cur
    52.75
    [cur
    51.75
     Cur
    50.75
    kur
    50.00
    _cur
    49.50
    Activations Density 0.020%

    No Known Activations