© 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. 41806
    Prev
    Next
    INDEX
    Explanations

    continuous functions

    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
    å¼ı设计
    -0.07
    orde
    -0.07
    haj
    -0.07
    bey
    -0.07
    cie
    -0.07
    å¼ıä¸Ń
    -0.07
    ä¼ļ议纪è¦ģ
    -0.06
    ajem
    -0.06
    ä¸İæĸ¹æ³ķ
    -0.06
    UTT
    -0.06
    POSITIVE LOGITS
    éĹŃ
    0.07
    ly
    0.07
    kof
    0.07
    kos
    0.07
    éħİ
    0.07
    ium
    0.07
    _cached
    0.07
    å¸Ĩ
    0.07
    .framework
    0.07
    عار
    0.07
    Activations Density 0.018%

    No Known Activations