© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20574
    Prev
    Next
    INDEX
    Explanations

    parts of documents or volumes

    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
    roud
    -0.09
    ymar
    -0.07
    ä¹ĭéģ¥
    -0.07
    urah
    -0.07
     universal
    -0.07
     murid
    -0.07
    universal
    -0.07
    æ¯įæł¡
    -0.06
    大åIJī
    -0.06
    ç²®
    -0.06
    POSITIVE LOGITS
     separate
    0.09
    åĪĨå¼Ģ
    0.08
    [--
    0.08
     Separate
    0.08
    两ä¸į误
    0.08
     seperate
    0.08
    åĪĨéĸĭ
    0.07
    æīĢæľīåĨħ容
    0.07
    åı¦è¡Į
    0.07
    ä¸Ģ份
    0.07
    Activations Density 0.007%

    No Known Activations