© 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. 19792
    Prev
    Next
    INDEX
    Explanations

    latitude and longitude coordinates

    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
    åĦ¿åŃIJçļĦ
    -0.07
    ChildIndex
    -0.07
    ä¸ĵç§ijåŃ¦æł¡
    -0.07
    ãĤĤãĤĬ
    -0.07
    æĪĸä¸İ
    -0.07
    æĪĸ缴æİ¥
    -0.07
    astle
    -0.06
    kaan
    -0.06
    诸æļ¨
    -0.06
    escu
    -0.06
    POSITIVE LOGITS
    夫å¦ĩ
    0.10
    çĶ·å¥³
    0.09
    夫婦
    0.08
    æŀķ
    0.08
     couple
    0.07
    ï¼Ĩ
    0.07
    utan
    0.07
     McB
    0.07
    æ°´å¹³åĴĮ
    0.07
    &
    0.07
    Activations Density 0.218%

    No Known Activations