© 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. 56339
    Prev
    Next
    INDEX
    Explanations

    religious terms and practices

    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
    åĴĮéĩįçĤ¹
    -0.07
    ä¸Ģæĸij
    -0.07
    çī©åĴĮ
    -0.07
    ниÑĨа
    -0.07
    kep
    -0.07
    èĥĥåı£
    -0.07
    天使
    -0.07
    åĴĮéĹ®é¢ĺ
    -0.07
    aison
    -0.07
    ieux
    -0.07
    POSITIVE LOGITS
    ä¼łç»Ł
    0.08
    ç«¯æľ¨
    0.07
    ä¼łç»ŁçļĦ
    0.07
     ritual
    0.07
    cion
    0.07
     Etiqu
    0.07
     beleg
    0.07
    unal
    0.07
     discipline
    0.07
     rituals
    0.07
    Activations Density 0.171%

    No Known Activations