© 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. 48581
    Prev
    Next
    INDEX
    Explanations

    integral, course, line, paths

    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
    ense
    -0.07
    ä¸ĢéŨ
    -0.07
    ellas
    -0.07
    arki
    -0.07
    ä¸Ĭä½į
    -0.07
     elusive
    -0.07
    /Index
    -0.07
     sund
    -0.07
    é¢Ħæµĭ
    -0.07
     legacy
    -0.07
    POSITIVE LOGITS
     enclosing
    0.08
    åij¨åĪ°
    0.08
    FileType
    0.07
    éģ¿å¼Ģ
    0.07
    éĹŃåIJĪ
    0.07
     contour
    0.07
     paths
    0.07
     intersect
    0.07
     cus
    0.07
    å°ıå¿ĥ
    0.07
    Activations Density 0.003%

    No Known Activations