© 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. 61512
    Prev
    Next
    INDEX
    Explanations

    mathematical operations or sequences

    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
     pomer
    -0.07
     dare
    -0.07
    ä»ĸæĿ¥
    -0.07
    ÎŃλ
    -0.07
    æĿ¥æĿ¥
    -0.07
     dared
    -0.06
    å¡ŀå°Ķ
    -0.06
    æĦıæ°Ķ
    -0.06
    lıkla
    -0.06
    WSC
    -0.06
    POSITIVE LOGITS
    Õ¡Õ®
    0.08
    ear
    0.07
    {}\
    0.07
    ')."
    0.07
    _serialize
    0.07
     заÑıви
    0.07
    jern
    0.06
    ografi
    0.06
    ä¸Ŀ毫
    0.06
    unden
    0.06
    Activations Density 0.073%

    No Known Activations