© 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. 15682
    Prev
    Next
    INDEX
    Explanations

    clinical symptoms

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

    No Comments

    Negative Logits
    泄漏
    -18.50
     leaked
    -17.75
     leak
    -17.50
     leaks
    -17.25
     leaking
    -16.50
    技术研发
    -16.50
     leakage
    -15.94
    メーカー
    -15.88
     telecom
    -15.75
    路桥
    -15.56
    POSITIVE LOGITS
    参
    18.25
    象
    17.88
    草
    16.75
    城
    16.63
    均匀
    16.50
     �
    16.00
    报
    15.88
    итет
    15.81
    酸
    15.63
    患者
    15.56
    Activations Density 0.352%

    No Known Activations