© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62039
    Prev
    Next
    INDEX
    Explanations

    forecast to year

    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
    enaar
    -0.08
    ç®ķ
    -0.08
    Forge
    -0.07
    é¦Ļåŀĭ
    -0.07
    ÑĪек
    -0.07
    inclus
    -0.07
    Clicked
    -0.07
    åĪ«
    -0.07
    ðŁĻĤ
    -0.07
    incontro
    -0.07
    POSITIVE LOGITS
    avor
    0.07
    ore
    0.07
     СоÑĢ
    0.07
    åĴĮå¿«ä¹IJ
    0.07
    èĩªå·±çļĦ人
    0.07
    iber
    0.07
    éĢĴ
    0.07
    纵
    0.06
    olin
    0.06
     ninh
    0.06
    Activations Density 0.049%

    No Known Activations