© 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. 1573
    Prev
    Next
    INDEX
    Explanations

    [political] => [political science]

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

    No Comments

    Negative Logits
    政治
    -69.00
     political
    -64.00
     politics
    -62.25
    Political
    -59.75
    的政治
    -59.00
     Political
    -58.50
     Politics
    -56.25
    political
    -55.50
     politically
    -50.50
    Politics
    -50.00
    POSITIVE LOGITS
    /fontawesome
    17.13
    菌
    14.56
     DATABASE
    14.56
     databases
    14.50
     Milwaukee
    14.38
    eka
    14.13
    光
    14.13
    DATABASE
    13.94
    abo
    13.88
    ım
    13.81
    Activations Density 0.221%

    No Known Activations