© 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. 1621
    Prev
    Next
    INDEX
    Explanations

    债务

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

    No Comments

    Negative Logits
    债务
    -20.38
     device
    -19.00
     poet
    -18.50
     Po
    -18.38
    device
    -17.88
    /device
    -17.63
     deviceId
    -17.00
     poems
    -16.88
    dance
    -16.75
    ற
    -16.75
    POSITIVE LOGITS
    CAL
    20.13
    gam
    19.75
     gam
    18.25
    flix
    18.13
     CALC
    17.88
     PIX
    17.75
     PIO
    17.50
     statistics
    17.50
     Mario
    17.13
     GAM
    16.88
    Activations Density 0.050%

    No Known Activations