© 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. 7490
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and code

    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
    ķĮ
    -0.07
    ä¸Ńåħ´
    -0.07
    agan
    -0.06
    çŃīæĿIJæĸĻ
    -0.06
    åĴĮè¡ĮåĬ¨
    -0.06
    =sub
    -0.06
     maxim
    -0.06
     buflen
    -0.06
    该æ¡Ī
    -0.06
    主干
    -0.06
    POSITIVE LOGITS
    isiv
    0.08
    uvi
    0.07
    åī
    0.07
    è¿İãģĪ
    0.07
    ponsored
    0.07
    sq
    0.07
    iq
    0.07
     Entret
    0.07
    мÑĸнÑĸ
    0.07
    менов
    0.07
    Activations Density 0.010%

    No Known Activations