© 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. 23969
    Prev
    Next
    INDEX
    Explanations

    canonical equations

    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
    ispers
    -0.07
    imas
    -0.07
    åįģæĿ¡
    -0.07
    ilding
    -0.07
    asso
    -0.07
    ture
    -0.07
    çļĦéĽª
    -0.07
    aru
    -0.07
    åĬłæĭ¿å¤§
    -0.07
    ä¸įæį¢
    -0.06
    POSITIVE LOGITS
    åħ«ä¹Ŀ
    0.07
    à¸ķัà¹īà¸ĩ
    0.07
    RICT
    0.07
    ä¸¥æł¼èIJ½å®ŀ
    0.07
    æĹ¥èµ·èĩ³
    0.07
    early
    0.07
    icode
    0.07
    åĢĴæķ°
    0.06
    onical
    0.06
    ä¸ĥåħ«
    0.06
    Activations Density 0.032%

    No Known Activations