© 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. 3817
    Prev
    Next
    INDEX
    Explanations

    XML and JSON structures

    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
    çİ®
    -0.07
    ábado
    -0.07
    æĹıèĩªæ²»åİ¿
    -0.07
    æ¡¥éķĩ
    -0.07
    æł¹æį®ä¸ªäºº
    -0.06
    ³
    -0.06
    ç«Ļåľ¨äºĨ
    -0.06
    åŁºåĩĨ
    -0.06
    .baidu
    -0.06
    °
    -0.06
    POSITIVE LOGITS
    缴éĢļ
    0.07
    eer
    0.07
    åįĹåĽ½
    0.07
    读åĪ°
    0.07
    æī®æ¼Ķ
    0.07
    å¤ļ
    0.07
    åĨįæİ¥
    0.07
    ä¸Ń游
    0.07
    enses
    0.06
    ERNEL
    0.06
    Activations Density 0.001%

    No Known Activations