© 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. 45562
    Prev
    Next
    INDEX
    Explanations

    Lagrangian, Lorentz, Laplacian

    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
    esome
    -0.09
    urance
    -0.08
    enticate
    -0.08
    ç´Ĺ
    -0.08
    деÑģÑıÑĤ
    -0.08
    æķ¢è¯´
    -0.08
    ersen
    -0.07
    ãģĦãģĨ
    -0.07
    IgnoreCase
    -0.07
    elow
    -0.07
    POSITIVE LOGITS
    ÙĬÙĨ
    0.08
    à¥į
    0.08
    мп
    0.08
    ting
    0.07
    Ö¼
    0.07
    ushima
    0.07
    sters
    0.07
    rowse
    0.06
    sztaÅĤ
    0.06
    zelfde
    0.06
    Activations Density 0.003%

    No Known Activations