© 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. 24872
    Prev
    Next
    INDEX
    Explanations

    quantum physics concepts or dynamics

    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
     cocci
    -0.08
     sex
    -0.08
    ingleton
    -0.07
    ç½ijæł¡
    -0.07
    ENTRY
    -0.07
     ÐĴойÑĤи
    -0.07
    ensä
    -0.07
    ovina
    -0.07
    ç²ĺèĨľ
    -0.07
    æł¡æŃ£
    -0.07
    POSITIVE LOGITS
     Hamilton
    0.09
    оÑĢа
    0.08
    è¯Ģ
    0.07
    å¼Ī
    0.07
     evolution
    0.07
     compression
    0.07
     tramp
    0.07
    ircuit
    0.07
    Hamilton
    0.07
    åIJĦé¢ĨåŁŁ
    0.07
    Activations Density 0.042%

    No Known Activations