© 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. 1529
    Prev
    Next
    INDEX
    Explanations

    communication

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

    No Comments

    Negative Logits
    字
    -19.13
     font
    -17.38
     Bach
    -16.50
    Fonts
    -16.25
     fonts
    -16.13
    bach
    -15.56
    ogenic
    -15.13
     Fonts
    -15.06
    Cro
    -15.00
     digits
    -14.88
    POSITIVE LOGITS
     security
    22.88
     cybersecurity
    19.75
     SECURITY
    18.63
    保安
    18.13
    security
    18.13
     Security
    18.00
     Beverly
    17.50
     exercise
    17.25
     Cyber
    17.13
    /security
    17.13
    Activations Density 0.399%

    No Known Activations