© 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. 31394
    Prev
    Next
    INDEX
    Explanations

    wave solutions, spring, year, male, Shader

    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
    æīĢèĥ½åıĬ
    -0.07
    unders
    -0.06
    à¸ĩ
    -0.06
    igel
    -0.06
    anas
    -0.06
    离
    -0.06
    wh
    -0.06
    osat
    -0.06
    ç«Ł
    -0.06
    åĽ
    -0.06
    POSITIVE LOGITS
    æĥħåĨµåĪĨæŀIJ
    0.08
    eber
    0.08
    uration
    0.07
    åĮħè£ħ设计
    0.07
    ivery
    0.07
    åįĥç§ĭ
    0.07
    rechn
    0.07
    空æ°Ķä¸ŃçļĦ
    0.07
    inition
    0.07
    vide
    0.07
    Activations Density 0.014%

    No Known Activations