© 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. 954
    Prev
    Next
    INDEX
    Explanations

    say countries

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

    No Comments

    Negative Logits
     qx
    -21.25
    qx
    -20.50
    wdx
    -19.25
    .Sql
    -19.00
    xdf
    -18.75
    VILLE
    -18.63
    xFE
    -18.50
    湾区
    -18.25
     Clubs
    -18.25
    dish
    -18.13
    POSITIVE LOGITS
     Russian
    15.56
    司机
    14.63
    俄国
    14.31
    印度
    13.69
     Hungary
    13.38
     Slovak
    13.19
    荆
    13.13
    俄罗斯
    13.13
     Hungarian
    13.13
     Montana
    13.13
    Activations Density 0.373%

    No Known Activations