© 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. 19859
    Prev
    Next
    INDEX
    Explanations

    Fourier series

    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
    ahoma
    -0.08
    é¥®æ°´æľº
    -0.07
    astle
    -0.07
    itto
    -0.07
    çĢļ
    -0.07
    æĭĶæ²³
    -0.07
    aining
    -0.07
    ovu
    -0.07
    gespr
    -0.07
    ToList
    -0.07
    POSITIVE LOGITS
    éĺ³åİ¿
    0.07
    lite
    0.07
     Lite
    0.07
    reuse
    0.07
    å¿ĥåĬ¨
    0.06
    .components
    0.06
     components
    0.06
     Components
    0.06
    ç»ĵæŀľæĺ¾ç¤º
    0.06
     ÙĤسÙħت
    0.06
    Activations Density 0.003%

    No Known Activations