© 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. 1757
    Prev
    Next
    INDEX
    Explanations

    say "sym"

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

    No Comments

    Negative Logits
    课堂教学
    -19.38
    课堂
    -18.88
    场比赛
    -18.63
    图书馆
    -18.50
    CAM
    -17.63
    okit
    -17.50
     cerebral
    -17.38
     оф
    -17.13
    _CONSOLE
    -17.13
     phi
    -16.88
    POSITIVE LOGITS
     Sym
    20.00
     symmetry
    17.50
    _sym
    17.13
    _sy
    16.88
    sym
    16.63
    Sym
    16.25
    音乐
    16.00
     symmetric
    15.63
     Bowie
    14.56
    /music
    14.38
    Activations Density 0.074%

    No Known Activations