© 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. 31878
    Prev
    Next
    INDEX
    Explanations

    artificial and synthetic materials

    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
    ieux
    -0.06
    idae
    -0.06
    iej
    -0.06
    enius
    -0.06
    åı£è¯Ģ
    -0.06
    å¤§ä¾ł
    -0.06
    åĴĮä¸ļåĬ¡
    -0.06
     hov
    -0.06
    hö
    -0.06
    ä½įç½®ä¸Ĭ
    -0.06
    POSITIVE LOGITS
    人工
    0.15
     artificial
    0.15
     synthetic
    0.14
     künst
    0.14
     artificially
    0.14
    人éĢł
    0.13
     manufactured
    0.13
    çļĦ人工
    0.12
     Synthetic
    0.12
    ificial
    0.12
    Activations Density 0.218%

    No Known Activations