© 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. 46973
    Prev
    Next
    INDEX
    Explanations

    population and census data

    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
     Postado
    -0.08
    ddy
    -0.08
    ç«ĻåĨħæIJľç´¢
    -0.08
     اÙĦجارÙĬ
    -0.08
    大å»Ī
    -0.08
    anj
    -0.08
    çİĦå¹»éŃĶæ³ķ
    -0.07
    feld
    -0.07
    æŃ¦ä¾łä¿®çľŁ
    -0.07
    æݨèįIJæľ¬ä¹¦
    -0.07
    POSITIVE LOGITS
    士
    0.06
    ãģ»
    0.06
    ossen
    0.06
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.06
    STRU
    0.05
    ippo
    0.05
    åı¯æĥ³èĢĮçŁ¥
    0.05
    stats
    0.05
    èĿ´
    0.05
    оÑĩе
    0.05
    Activations Density 0.283%

    No Known Activations