© 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. 1507
    Prev
    Next
    INDEX
    Explanations

    [AI] => [assistant]

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

    No Comments

    Negative Logits
     artificial
    -26.63
     Artificial
    -25.38
    _AI
    -24.00
    人工智能
    -23.13
    AI
    -22.88
     искусств
    -22.25
     AI
    -21.63
    人造
    -21.00
    -AA
    -20.63
    Ai
    -19.75
    POSITIVE LOGITS
     BR
    13.31
     Dota
    13.13
    ython
    13.06
     Crist
    13.00
    urt
    12.50
    BR
    12.50
    ela
    12.44
     Uber
    12.25
    $
    12.00
    allel
    11.94
    Activations Density 0.019%

    No Known Activations