© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30044
    Prev
    Next
    INDEX
    Explanations

    first of

    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
    laki
    -0.08
    Į¨
    -0.08
    _INCREMENT
    -0.08
    åĽ¾çīĩæĿ¥æºIJäºİç½ij绾
    -0.08
     reluct
    -0.07
    xaa
    -0.07
    æİĸ
    -0.07
    ç¥IJ
    -0.07
    .Clock
    -0.07
     soud
    -0.07
    POSITIVE LOGITS
    ived
    0.07
    ief
    0.06
    Ex
    0.06
    ifu
    0.06
    بت
    0.06
    ноÑģÑĤÑĮÑİ
    0.06
    .ms
    0.06
     Ex
    0.06
    é«ĺçĥ§
    0.06
    ex
    0.06
    Activations Density 0.210%

    No Known Activations