© 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. 27296
    Prev
    Next
    INDEX
    Explanations

    complex numbers and mathematical notation

    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
    ãĥĥãĤ³
    -0.09
    ä¸įåĢĴ
    -0.08
    atchet
    -0.08
    Ø´Ùħ
    -0.08
    ajat
    -0.07
    .transition
    -0.07
    manuel
    -0.07
    ipse
    -0.07
    çļĦä¸Ģå¥Ĺ
    -0.07
    çļĦåħ¨éĥ¨åĨħ容
    -0.07
    POSITIVE LOGITS
    ermo
    0.07
    /gui
    0.07
    _imag
    0.07
     drifted
    0.06
    å¹³è¡Į
    0.06
     ventured
    0.06
    голо
    0.06
    dul
    0.06
    å²ij
    0.06
     drift
    0.06
    Activations Density 0.003%

    No Known Activations