© 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. 16791
    Prev
    Next
    INDEX
    Explanations

    spherical and polar coordinates

    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
    æ°´å¹³
    -0.07
    容
    -0.07
    ungsweise
    -0.07
    itar
    -0.06
    ugio
    -0.06
    çļĦåīįæĻ¯
    -0.06
    unes
    -0.06
    è·¯
    -0.06
     Samedi
    -0.06
    åĬŀ
    -0.06
    POSITIVE LOGITS
     polar
    0.10
     Aires
    0.08
    æĸ¹ä½į
    0.08
    imuth
    0.08
    itical
    0.08
    oord
    0.07
    atisf
    0.07
    leigh
    0.07
     بÛĮÙĨÛĮ
    0.07
     polarization
    0.07
    Activations Density 0.007%

    No Known Activations