© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47524
    Prev
    Next
    INDEX
    Explanations

    eigenvalues and eigenvectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ngo
    -0.07
    oulder
    -0.07
    è°ĥåĪ°
    -0.07
    olland
    -0.07
    충
    -0.07
    rella
    -0.07
    缺ä¸Ģ
    -0.07
    itto
    -0.07
    寸
    -0.07
    essin
    -0.07
    POSITIVE LOGITS
     sorted
    0.09
    æİĴåºı
    0.08
     eig
    0.08
     SEEK
    0.08
     eign
    0.08
     sorting
    0.08
    sorted
    0.08
     eigen
    0.08
     ordered
    0.08
    _sorted
    0.07
    Activations Density 0.012%

    No Known Activations