© 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. 33900
    Prev
    Next
    INDEX
    Explanations

    php site

    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
    ells
    -0.07
    æ°Ľ
    -0.07
    è¡
    -0.07
     borne
    -0.07
    uze
    -0.07
    ashboard
    -0.06
    _Base
    -0.06
    anis
    -0.06
    ä¸Ĭæĺł
    -0.06
    å°ı鸡
    -0.06
    POSITIVE LOGITS
     nanti
    0.09
    åIJİç»Ń
    0.09
     subsequent
    0.08
     later
    0.07
    yclopedia
    0.07
    raud
    0.07
    åIJİç»ŃçļĦ
    0.07
    pora
    0.07
     calculations
    0.07
    以åIJİçļĦ
    0.07
    Activations Density 0.076%

    No Known Activations