© 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. 1068
    Prev
    Next
    INDEX
    Explanations

    pixel

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

    No Comments

    Negative Logits
     pixel
    -44.75
    像素
    -42.75
     Pixel
    -40.75
    pixel
    -40.75
    _PIXEL
    -40.25
    Pixel
    -39.75
    _pixel
    -38.50
     pixels
    -38.50
    pixels
    -36.50
     Pixels
    -35.25
    POSITIVE LOGITS
    俄国
    16.13
    图书馆
    15.56
    语文
    15.38
     Russian
    15.25
    lya
    15.13
     Serg
    15.13
    edith
    15.00
    南宋
    14.94
     pym
    14.88
    语言
    14.88
    Activations Density 0.050%

    No Known Activations