© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15660
    Prev
    Next
    INDEX
    Explanations

    [surname] => [surname]

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

    No Comments

    Negative Logits
     QU
    -30.25
     Qu
    -29.75
     Quart
    -29.63
    qu
    -29.13
    quil
    -29.00
     ql
    -28.88
    Qu
    -28.75
    .Qu
    -28.50
    qd
    -28.50
    QU
    -28.38
    POSITIVE LOGITS
     Rodr
    15.63
    UNG
    15.56
    动力电池
    14.94
    皮革
    14.69
     Banner
    14.69
     cond
    14.50
    电线
    14.44
    導
    14.19
    CAM
    13.94
    导
    13.88
    Activations Density 0.899%

    No Known Activations