© 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. 1235
    Prev
    Next
    INDEX
    Explanations

    hole

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

    No Comments

    Negative Logits
    孔子
    -17.50
    公安
    -15.44
    警
    -15.38
    密码
    -15.31
    sie
    -15.06
     Alabama
    -15.00
     Gum
    -14.94
    Facebook
    -14.69
    signal
    -14.63
    facebook
    -14.50
    POSITIVE LOGITS
    .communication
    19.75
    羽毛
    19.38
    农场
    18.88
     farms
    18.38
     Farms
    17.38
    影视剧
    17.13
     aeros
    16.75
    戏剧
    16.63
    蒸汽
    16.50
     macro
    16.38
    Activations Density 0.404%

    No Known Activations