© 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. 14584
    Prev
    Next
    INDEX
    Explanations

    self‑confidence phrases

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

    No Comments

    Negative Logits
    otas
    -19.25
    odom
    -18.50
    vos
    -18.38
    exas
    -17.88
    vas
    -17.13
    ascar
    -16.75
    oser
    -16.63
    嵇
    -16.63
    urator
    -16.63
    .setModel
    -16.50
    POSITIVE LOGITS
     Hancock
    21.88
    احت
    19.75
    imp
    19.00
    upe
    18.13
    _imp
    18.13
     الاحت
    18.00
    用电
    17.88
    ULT
    17.63
    Tooltip
    17.38
    溥
    17.25
    Activations Density 0.786%

    No Known Activations