© 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. 2405
    Prev
    Next
    INDEX
    Explanations

    say C keywords

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

    No Comments

    Negative Logits
     Django
    -18.25
     CRM
    -15.88
     Kak
    -14.88
    JR
    -14.75
    ouston
    -14.50
    ancer
    -14.38
    鹊
    -14.31
    柿
    -14.13
     Industry
    -13.94
     elephant
    -13.94
    POSITIVE LOGITS
    花样
    15.75
    省市
    15.75
    坞
    15.06
    展览会
    15.06
    ///<
    14.94
     sluts
    14.94
    irth
    14.69
    ein
    14.63
     secular
    14.50
    /thread
    14.44
    Activations Density 0.037%

    No Known Activations