© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1205
    Prev
    Next
    INDEX
    Explanations

    UN Security Council

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

    No Comments

    Negative Logits
     art
    -16.75
    mat
    -16.38
    mast
    -15.75
    construction
    -15.38
    工程施工
    -15.19
    pole
    -14.94
     construction
    -14.75
     math
    -14.69
     Art
    -14.69
    mate
    -14.44
    POSITIVE LOGITS
    SCRIPT
    18.88
     picture
    17.88
    ектив
    17.63
    元
    17.50
    中国足球
    17.25
     Pictures
    17.13
     Metropolitan
    17.13
    Pictures
    17.13
    经济学家
    16.88
     caracteres
    16.75
    Activations Density 0.275%

    No Known Activations