© 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. 15447
    Prev
    Next
    INDEX
    Explanations

    ischemic stroke

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

    No Comments

    Negative Logits
    ProductId
    -16.50
    的品牌
    -16.25
    品牌的
    -16.00
     MATERIAL
    -15.38
    bour
    -15.25
    品牌
    -15.13
    生产商
    -15.00
    ListComponent
    -14.94
    PackageName
    -14.88
    .Brand
    -14.88
    POSITIVE LOGITS
    塞
    17.38
    堵塞
    17.00
     EVT
    16.88
     clot
    16.50
    림
    15.88
    ict
    15.44
    梗
    15.25
     Ere
    15.25
     Event
    15.19
    栓
    15.13
    Activations Density 0.082%

    No Known Activations