© 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. 1833
    Prev
    Next
    INDEX
    Explanations

    say acronyms

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

    No Comments

    Negative Logits
     reading
    -46.00
     read
    -45.75
    读
    -44.25
     READ
    -43.75
    讀
    -43.00
     reads
    -42.75
     Reading
    -42.75
     Read
    -42.75
    阅读
    -42.75
     readings
    -40.75
    POSITIVE LOGITS
    ости
    14.94
    FPS
    14.56
    fps
    14.38
    CSI
    14.06
     Jes
    13.56
    _fps
    13.19
    OSC
    13.19
    IPS
    13.00
    نج
    12.88
    -car
    12.81
    Activations Density 0.273%

    No Known Activations