© 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. 56464
    Prev
    Next
    INDEX
    Explanations

    slow, slower, minority

    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
    æł©æł©
    -0.08
    archy
    -0.07
    erry
    -0.07
    åĺ´ä¸Ĭ
    -0.07
    é£İå°ĺ
    -0.07
    æĪĢ
    -0.07
    æīĭåı¯
    -0.07
    opp
    -0.07
    ksom
    -0.07
    à°
    -0.07
    POSITIVE LOGITS
    çŁŃæĿ¿
    0.07
    æ°´å¹³çļĦ
    0.07
     slower
    0.07
     slow
    0.07
     minority
    0.07
    tol
    0.06
    æľĢçŁŃ
    0.06
    ulte
    0.06
    è±ģ
    0.06
    åħ±åIJĮçļĦ
    0.06
    Activations Density 0.016%

    No Known Activations