© 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. 31110
    Prev
    Next
    INDEX
    Explanations

    arithmetic sequence terms

    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
    urai
    -0.07
    ç´¯çļĦ
    -0.06
     duplicated
    -0.06
    qli
    -0.06
    ä¸įå°ij人
    -0.06
    PTY
    -0.06
    awah
    -0.06
    å¹´å¢ŀéķ¿
    -0.06
    pie
    -0.06
    ahl
    -0.06
    POSITIVE LOGITS
    åĪ«æĹł
    0.07
    atif
    0.07
    çIJIJ
    0.07
    гÑĸд
    0.06
    ÑĹв
    0.06
    èĭŀ
    0.06
    å¾·éŁ³
    0.06
    ló
    0.06
    .Inf
    0.06
    à¸Ľà¸£à¸°à¸Ĭ
    0.06
    Activations Density 0.012%

    No Known Activations