© 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. 14019
    Prev
    Next
    INDEX
    Explanations

    say academic

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

    No Comments

    Negative Logits
    项目建设
    -20.13
    市公安局
    -17.88
    项目的
    -17.88
    项目
    -17.63
    项目经理
    -17.00
    -monitor
    -16.75
    edImage
    -16.63
    OfWork
    -16.50
    project
    -16.25
    监测
    -16.25
    POSITIVE LOGITS
    .ease
    16.13
    (domain
    15.88
    学术
    15.38
     Kore
    14.88
     representa
    14.75
     domaine
    14.75
     academia
    14.63
     scholarly
    14.56
     domain
    14.56
    mount
    14.44
    Activations Density 0.345%

    No Known Activations