© 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. 1586
    Prev
    Next
    INDEX
    Explanations

    Hebrew

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

    No Comments

    Negative Logits
    以色列
    -26.88
     Israel
    -26.38
    Israel
    -26.00
     Biblical
    -24.25
    圣经
    -23.88
    -Israel
    -23.25
     biblical
    -22.13
     Israeli
    -21.25
     Zionist
    -21.13
     bible
    -20.00
    POSITIVE LOGITS
    卡
    16.50
    勇敢
    16.13
    _card
    15.31
     hospital
    15.25
     Hospital
    14.75
    院
    14.75
    山
    14.69
    英语
    14.63
     Card
    14.56
    -card
    14.44
    Activations Density 0.386%

    No Known Activations