© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14815
    Prev
    Next
    INDEX
    Explanations

    say Turkish

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

    No Comments

    Negative Logits
    配方
    -19.38
    技术
    -19.38
    看电影
    -18.25
    追踪
    -17.88
    AUT
    -17.75
     输入
    -17.25
     Summers
    -16.63
    输入
    -16.63
    Slim
    -16.25
     formulas
    -16.00
    POSITIVE LOGITS
     dönemin
    13.75
    保護
    12.88
    窝
    12.69
    ->{
    12.56
     kurulu
    12.13
     eğ
    12.00
    uç
    12.00
     güneş
    11.94
    ç
    11.94
    LEFT
    11.88
    Activations Density 0.021%

    No Known Activations