© 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. 1900
    Prev
    Next
    INDEX
    Explanations

    [Communication] => [Communication]

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

    No Comments

    Negative Logits
     communication
    -58.75
     Communication
    -56.25
    Communication
    -55.75
    通信
    -55.75
     communications
    -52.75
     communicate
    -50.25
     Communic
    -49.75
    communication
    -49.50
     communicated
    -48.25
    communications
    -48.00
    POSITIVE LOGITS
    ArrayType
    17.38
     Bav
    16.88
    矩阵
    16.25
     Harry
    15.69
    _numpy
    14.81
    趾
    14.31
    zung
    14.19
     luz
    14.13
    Harry
    14.06
    �单
    14.00
    Activations Density 0.204%

    No Known Activations