© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14524
    Prev
    Next
    INDEX
    Explanations

    time multiplication

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

    No Comments

    Negative Logits
    riz
    -17.50
    owi
    -15.94
    afen
    -15.75
     purse
    -15.69
    矛
    -15.31
    …↵↵↵↵
    -15.19
    itta
    -15.00
     legalization
    -14.75
    shine
    -14.69
    loh
    -14.56
    POSITIVE LOGITS
    actus
    18.00
     sleeper
    13.00
    CAM
    12.38
     cam
    12.25
    aturday
    12.19
    ATAR
    12.19
     endTime
    12.00
    一天
    12.00
    ctime
    12.00
    /activity
    11.88
    Activations Density 0.015%

    No Known Activations