© 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. 49905
    Prev
    Next
    INDEX
    Explanations

    governance and its related terms

    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
    ness
    -0.12
    ingly
    -0.09
    leton
    -0.09
    sWith
    -0.09
    aneous
    -0.08
    ation
    -0.08
    ç»Ŀ伦
    -0.08
    Æ°á»Ľp
    -0.08
    erior
    -0.07
    ity
    -0.07
    POSITIVE LOGITS
    ä¸įåĸĦ
    0.08
    گرÛĮ
    0.08
    egn
    0.08
    bourg
    0.08
    hog
    0.08
    ê¹IJ
    0.07
    ested
    0.07
    esp
    0.07
    este
    0.07
    /control
    0.07
    Activations Density 0.012%

    No Known Activations