© 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. 18586
    Prev
    Next
    INDEX
    Explanations

    bibliographie.bib

    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
    è¾¾æĭī
    -0.08
    èī²åĪĹ
    -0.07
    ufa
    -0.07
     Sed
    -0.07
    ãĤ¤ãĥĦ
    -0.07
    mailto
    -0.07
    å§ĭ
    -0.07
    人æ°ijæĶ¿åºľ
    -0.07
    mino
    -0.07
    sed
    -0.07
    POSITIVE LOGITS
    æĿ¥æºIJç½ij绾
    0.07
    ä¸įå®Į
    0.07
     radic
    0.07
     /^(
    0.06
    ardt
    0.06
    æĿ¥èĩªä¸ŃåĽ½
    0.06
    egie
    0.06
    avia
    0.06
     Utils
    0.06
    addAll
    0.06
    Activations Density 0.001%

    No Known Activations