© 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. 14627
    Prev
    Next
    INDEX
    Explanations

    9

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

    No Comments

    Negative Logits
    七个
    -16.63
    六个
    -16.50
    第六
    -15.81
    ⼋
    -15.13
    istics
    -14.69
    戏
    -14.56
    八个
    -14.19
     расс
    -14.06
    九大
    -14.06
     newsp
    -13.94
    POSITIVE LOGITS
    淳
    19.63
     Astroph
    19.25
     ether
    18.63
    ETHER
    17.88
     rho
    17.75
    Thor
    17.63
     Pty
    17.38
     Telegraph
    17.00
    avax
    16.75
     Ether
    16.75
    Activations Density 0.054%

    No Known Activations