© 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. 2039
    Prev
    Next
    INDEX
    Explanations

    say mathematics

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

    No Comments

    Negative Logits
     car
    -46.25
     cars
    -44.75
    车
    -43.75
     Cars
    -42.25
    汽车
    -41.25
    _CAR
    -41.00
    Cars
    -40.75
    车辆
    -39.50
    Car
    -38.25
    汽車
    -38.25
    POSITIVE LOGITS
    数学
    15.94
     mathematical
    14.63
     spectrum
    14.00
    (BigInteger
    13.88
     Hull
    13.75
    DLL
    13.75
    媒体
    13.69
     mathematics
    13.25
     Spectrum
    13.25
     Bayesian
    13.00
    Activations Density 0.200%

    No Known Activations