© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14941
    Prev
    Next
    INDEX
    Explanations

    bacterial Gram classification

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

    No Comments

    Negative Logits
    rowData
    -18.63
    霄
    -18.50
     newRow
    -18.25
    巫
    -17.63
    roomId
    -16.88
    .Tele
    -16.75
    乡村旅游
    -16.63
    DataRow
    -16.38
    铎
    -16.13
     tileSize
    -15.94
    POSITIVE LOGITS
    .delay
    13.63
    评价
    13.56
    -peer
    12.94
     langu
    12.56
     surrounds
    12.13
    评议
    11.88
    ercise
    11.75
    ment
    11.69
    语言
    11.63
     eng
    11.25
    Activations Density 0.074%

    No Known Activations