© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1599
    Prev
    Next
    INDEX
    Explanations

    Buddhist terms

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

    No Comments

    Negative Logits
    AC
    -31.00
     AC
    -28.75
    Architecture
    -27.75
    Art
    -27.50
     architecture
    -26.88
    人工智能
    -26.63
     Architecture
    -26.50
     architectural
    -25.75
    ACY
    -25.63
     Acid
    -25.63
    POSITIVE LOGITS
    a
    14.31
    鹃
    13.44
    .LOG
    12.56
    伽
    11.88
    �
    11.88
    乐
    11.81
    ќ
    11.75
    óst
    11.69
     mente
    11.63
    XC
    11.56
    Activations Density 0.683%

    No Known Activations