© 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. 1925
    Prev
    Next
    INDEX
    Explanations

    say math

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

    No Comments

    Negative Logits
     jazz
    -23.38
    _music
    -23.25
     music
    -23.25
     Music
    -23.13
    /music
    -23.00
    音乐
    -22.88
     Musik
    -22.63
    Music
    -22.38
     Jazz
    -21.75
    music
    -20.88
    POSITIVE LOGITS
     mathematics
    16.88
    数学
    16.00
     Mathematics
    15.63
    math
    15.19
     mathematical
    14.69
     math
    14.06
     educating
    13.94
     mathematic
    13.81
    aths
    13.75
     educate
    13.69
    Activations Density 0.035%

    No Known Activations