© 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. 2855
    Prev
    Next
    INDEX
    Explanations

    modal

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

    No Comments

    Negative Logits
    曲
    -23.88
     ref
    -19.25
    (cur
    -17.38
     cur
    -17.13
     curved
    -16.50
    moid
    -16.25
    (ref
    -16.25
    cur
    -15.94
    积
    -15.81
    [cur
    -15.69
    POSITIVE LOGITS
     modal
    75.50
    modal
    70.00
     Modal
    68.50
    Modal
    65.50
    .modal
    62.25
    /modal
    61.50
    _modal
    61.50
    -modal
    58.50
    _MODAL
    53.50
    (mod
    52.25
    Activations Density 0.044%

    No Known Activations