© 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. 18574
    Prev
    Next
    INDEX
    Explanations

    physics equations and variables

    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
     aka
    -0.06
    rement
    -0.06
    thal
    -0.06
    iale
    -0.06
    èĨĢ
    -0.06
    quisite
    -0.06
    .look
    -0.06
    etim
    -0.06
    ç£Ĭ
    -0.06
    itale
    -0.06
    POSITIVE LOGITS
    felder
    0.08
    å·´å¡ŀ
    0.08
    _hooks
    0.08
    çļĦäºĭæĥħäºĨ
    0.08
    amber
    0.07
    rico
    0.07
    æĪijåIJ§
    0.07
    æ¼Ķ
    0.07
    æĸ°åĬłåĿ¡
    0.07
    aphore
    0.07
    Activations Density 0.003%

    No Known Activations