© 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. 24518
    Prev
    Next
    INDEX
    Explanations

    substitution patterns

    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
     подвод
    -0.08
    alay
    -0.07
    ä¿®éķ¿
    -0.07
    å±Ĥ
    -0.07
    érique
    -0.07
     debit
    -0.07
    /play
    -0.07
    æĿIJæĸĻåĴĮ
    -0.07
    éĢĶä¸Ń
    -0.07
    apas
    -0.07
    POSITIVE LOGITS
    idente
    0.08
    uent
    0.08
    å¸ĥå±Ģ
    0.08
    æĸ¹ä½į
    0.07
    åºķèī²
    0.07
    空çĻ½
    0.07
    retty
    0.07
    缸éļĶ
    0.07
    venta
    0.07
     pattern
    0.07
    Activations Density 0.032%

    No Known Activations