© 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. 14447
    Prev
    Next
    INDEX
    Explanations

    line‑ending comma

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

    No Comments

    Negative Logits
     Hancock
    -21.63
    احت
    -19.50
    imp
    -18.88
     الاحت
    -18.50
    upe
    -18.38
    _imp
    -18.25
    用电
    -18.00
    郢
    -18.00
     implic
    -17.63
    Tooltip
    -17.50
    POSITIVE LOGITS
    vos
    18.00
    otas
    17.88
    odom
    17.25
    exas
    16.75
    urator
    16.75
    vas
    16.63
    oser
    16.50
    .setModel
    16.25
    aras
    15.94
    嵇
    15.81
    Activations Density 0.818%

    No Known Activations