© 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. 62087
    Prev
    Next
    INDEX
    Explanations

    year and dates

    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
    ä¸ĭåij¨
    -0.08
    rava
    -0.08
    èħ°
    -0.08
    çľ¼ä¸ĭ
    -0.07
    ä¸Ģ段æŶéĹ´åIJİ
    -0.07
    rts
    -0.07
     tonight
    -0.07
    æĽ´æĸ°äºİ
    -0.07
    ulares
    -0.07
    第äºĮ天
    -0.07
    POSITIVE LOGITS
    è·Ŀä»Ĭ
    0.10
    年份
    0.10
     dates
    0.10
     YYYY
    0.10
     date
    0.10
     year
    0.09
    /year
    0.09
    éĤ£ä¸Ģå¹´
    0.08
    date
    0.08
     calendar
    0.08
    Activations Density 0.176%

    No Known Activations