© 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. 1955
    Prev
    Next
    INDEX
    Explanations

    [IoT] => [IoT]

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

    No Comments

    Negative Logits
     theology
    -18.63
     theological
    -18.13
    物流公司
    -17.75
    =log
    -17.63
     jsonString
    -17.38
    地理
    -17.38
    工业
    -17.25
    逻辑
    -17.13
    物联网
    -16.88
    Θ
    -16.88
    POSITIVE LOGITS
     sym
    17.38
    lsa
    16.63
    Sym
    16.50
     Sym
    15.56
     sympt
    15.06
    _sym
    14.75
    .sym
    14.69
    еж
    14.56
    SYM
    14.13
     Canada
    14.06
    Activations Density 0.127%

    No Known Activations