© 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. 56372
    Prev
    Next
    INDEX
    Explanations

    integer sequences and numerical series

    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
    auan
    -0.08
    à¹Ģรืà¸Ńà¸Ļ
    -0.08
    croft
    -0.08
    yre
    -0.08
    .cg
    -0.07
    emaal
    -0.07
    Ñĩей
    -0.07
    ourcem
    -0.07
    åĴĮå°ļ
    -0.07
    ä¹ĭæĢ¥
    -0.07
    POSITIVE LOGITS
    etc
    0.07
    ãģ¨ãģĦãģ£ãģŁ
    0.07
     etc
    0.07
    ลฯ
    0.07
    ander
    0.06
     till
    0.06
    æ´¥
    0.06
    _|
    0.06
    çıĬçıĬ
    0.06
    åıªè¦ģæĺ¯
    0.06
    Activations Density 0.012%

    No Known Activations