© 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. 24177
    Prev
    Next
    INDEX
    Explanations

    monocytes, macrophages, LDL, oocytes

    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
    iba
    -0.06
    кÑĢо
    -0.06
    æį£
    -0.06
    æ¾İæ¹ĸ
    -0.06
    existent
    -0.06
    klin
    -0.06
    ieri
    -0.05
    ichael
    -0.05
    {text
    -0.05
    ages
    -0.05
    POSITIVE LOGITS
    åѤ
    0.09
    ä¼ļåIJĮ
    0.09
     dikat
    0.08
    åѤç«ĭ
    0.08
    éĢļè¿ĩä¸İ
    0.08
    æīĢå¤ĦçļĦ
    0.08
    åij¨åĽ´çļĦ
    0.08
     주ë³ĢìĿĺ
    0.08
    opak
    0.08
     surrounded
    0.07
    Activations Density 0.119%

    No Known Activations