© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14348
    Prev
    Next
    INDEX
    Explanations

    angiosperms

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

    No Comments

    Negative Logits
    ório
    -16.25
    均衡
    -15.94
    cba
    -15.75
    Uri
    -15.63
    бал
    -15.56
    emet
    -15.56
    ĩ
    -15.44
    𝑈
    -14.56
    _ur
    -14.56
    wealth
    -14.50
    POSITIVE LOGITS
    /angular
    14.88
     woodland
    14.13
    男
    13.75
    模拟
    13.63
     modele
    13.63
     shaving
    13.50
    قة
    13.38
     study
    13.31
    _GR
    13.13
    买
    12.81
    Activations Density 0.039%

    No Known Activations