© 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. 1306
    Prev
    Next
    INDEX
    Explanations

    Determines, patented, logic, process

    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
    èݱ德
    -0.09
    å¼Ī
    -0.08
    пеÑĤи
    -0.08
    èĭ¥èĥ½
    -0.08
    CharacterSet
    -0.08
     Decompiled
    -0.08
    åĪĺå¿Ĺ
    -0.08
    attere
    -0.07
    大åĬĽåıijå±ķ
    -0.07
     easily
    -0.07
    POSITIVE LOGITS
    åľ¨æ¯ı个
    0.08
    æ¯ıæĻļ
    0.08
    æĺ¯æł¹æį®
    0.07
    æ¯ı天æĻļä¸Ĭ
    0.07
    ä¼ļæł¹æį®
    0.07
    aho
    0.07
     пÑĢоизводиÑĤÑģÑı
    0.07
    æ¯ı天æĹ©ä¸Ĭ
    0.07
     determines
    0.07
     patented
    0.07
    Activations Density 0.034%

    No Known Activations