© 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. 1812
    Prev
    Next
    INDEX
    Explanations

    immune

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

    No Comments

    Negative Logits
    lict
    -19.13
    lement
    -17.38
    abar
    -17.25
    汇集
    -16.38
     kiện
    -16.25
    .IC
    -16.13
    igrant
    -15.69
    lements
    -15.56
    .dm
    -15.44
    IMUM
    -15.38
    POSITIVE LOGITS
     Rahul
    15.94
    蕖
    15.25
     asia
    15.13
    _NAV
    14.63
    .Navigation
    14.50
     veter
    14.44
    新中国
    14.31
     graft
    14.25
     Sue
    13.88
    老大
    13.69
    Activations Density 0.007%

    No Known Activations