© 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. 63274
    Prev
    Next
    INDEX
    Explanations

    Sub-Saharan Africa

    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
    éter
    -0.07
    onat
    -0.07
    åľ¨åı°
    -0.07
    ä¸įåħ¥
    -0.07
    溶äºİ
    -0.07
    deen
    -0.07
    eed
    -0.07
    йко
    -0.07
    åĻĹ
    -0.07
    æĢ»åı°
    -0.07
    POSITIVE LOGITS
    -wide
    0.07
    iches
    0.07
    æĺ¯æĢİæł·çļĦ
    0.06
    /*/
    0.06
    alainen
    0.06
    vier
    0.06
    åľ°åĮºçļĦ
    0.06
    ستاÙĨÛĮ
    0.06
    ieri
    0.06
    ä¹ĭè¡Į
    0.06
    Activations Density 0.054%

    No Known Activations