© 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. 13010
    Prev
    Next
    INDEX
    Explanations

    -ation, -ogenesis, -ynthesis

    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
    sek
    -0.07
    velt
    -0.07
    mig
    -0.07
    odz
    -0.07
    è±
    -0.07
    çŁ¥è¯ĨåĴĮæĬĢèĥ½
    -0.07
    åľ¨æľ¬æ¬¡
    -0.06
    åºĨ
    -0.06
    à¸Ķà¹ī
    -0.06
     Wagen
    -0.06
    POSITIVE LOGITS
     whereby
    0.09
    åıijçĶŁåľ¨
    0.09
    ä¸ĢåĽŀäºĭ
    0.09
    ä¸Ģè¯į
    0.09
    æĺ¯æĮĩ
    0.08
    Ïĩη
    0.07
    ção
    0.07
    è¿Ļ个è¯į
    0.07
    .colorbar
    0.07
    Quiet
    0.07
    Activations Density 0.008%

    No Known Activations