© 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. 62586
    Prev
    Next
    INDEX
    Explanations

    smoothness and continuous functions

    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
    è´«ç©·
    -0.07
    èĦ¯
    -0.07
    _arrow
    -0.07
     вмеÑģÑĤ
    -0.07
    èĩ´çļĦ
    -0.06
     Trop
    -0.06
    è´«
    -0.06
    eref
    -0.06
    ä¹ı
    -0.06
    ror
    -0.06
    POSITIVE LOGITS
    wig
    0.08
     taper
    0.08
    æŁĶåĴĮ
    0.08
     smoothly
    0.08
    .interpolate
    0.07
    nice
    0.07
    bounded
    0.07
    ä¿®æķ´
    0.07
    ENSOR
    0.07
    kra
    0.07
    Activations Density 0.009%

    No Known Activations