© 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. 27024
    Prev
    Next
    INDEX
    Explanations

    empirical tests and validation

    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
    misc
    -0.08
    ê°IJìĿĦ
    -0.08
    ê°IJìĿ´
    -0.07
    remen
    -0.07
     Catan
    -0.07
    ãģªãģĮ
    -0.07
    ioned
    -0.07
    ê°IJê³¼
    -0.07
    DIRECTORY
    -0.07
    ä»ĭ
    -0.07
    POSITIVE LOGITS
    æ£ĢéªĮ
    0.14
    éªĮè¯ģ
    0.12
     testing
    0.10
     validating
    0.10
     tests
    0.10
     validation
    0.10
     test
    0.09
    檢é©Ĺ
    0.09
    é©ĹèŃī
    0.09
     пÑĢовеÑĢки
    0.09
    Activations Density 0.017%

    No Known Activations