© 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. 1908
    Prev
    Next
    INDEX
    Explanations

    say academic fields

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

    No Comments

    Negative Logits
     Academic
    -44.50
     academic
    -44.25
    Ac
    -42.25
    academic
    -42.00
    学术
    -41.75
    酸
    -38.25
    _ac
    -37.25
    acid
    -37.25
     acad
    -36.25
     Acad
    -36.25
    POSITIVE LOGITS
     porter
    13.88
    羽
    13.69
    licht
    13.44
     Lynch
    13.00
    雲
    12.94
    云
    12.81
    ittel
    12.75
    elson
    12.69
    amma
    12.56
    り
    12.56
    Activations Density 0.092%

    No Known Activations