© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14916
    Prev
    Next
    INDEX
    Explanations

    say medical

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

    No Comments

    Negative Logits
    %
↵
    -16.25
    萬
    -16.00
     
    -16.00
    otine
    -15.13
    ấn
    -14.81
    .telegram
    -14.50
    '''
↵
    -14.44
    
↵
    -14.19
    
↵

↵
    -14.06
     

↵
    -14.06
    POSITIVE LOGITS
    肤
    16.38
    去医院
    15.50
     hospital
    14.94
    clinical
    14.88
    人民医院
    14.81
    临床
    14.63
     Veter
    14.25
    鸡肉
    14.25
    verte
    14.19
    -bre
    13.88
    Activations Density 0.217%

    No Known Activations