© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14410
    Prev
    Next
    INDEX
    Explanations

    African

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

    No Comments

    Negative Logits
    Jets
    -19.25
    IRS
    -16.50
    隙
    -15.88
     MSI
    -15.63
    ISP
    -14.88
    iks
    -14.81
    ARGET
    -14.75
    苴
    -14.75
    xies
    -14.75
    igest
    -14.69
    POSITIVE LOGITS
    Africa
    15.44
    リア
    14.88
     ern
    14.56
     PAC
    14.31
     Africa
    14.13
     Tahoe
    14.06
     Korea
    13.94
    ifty
    13.94
    berg
    13.81
     tropical
    13.75
    Activations Density 0.045%

    No Known Activations