© 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. 64127
    Prev
    Next
    INDEX
    Explanations

    vascularization and networks

    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
     gege
    -0.08
    ArrayOf
    -0.08
    èĴ¸èĴ¸
    -0.08
    个æĪĸå¤ļ个
    -0.08
    /false
    -0.08
    ä¼łç»Łäº§ä¸ļ
    -0.07
    ائÙħ
    -0.07
    姿
    -0.07
     BATCH
    -0.07
    åĵįå½»
    -0.07
    POSITIVE LOGITS
     endoth
    0.09
    åı£çļĦ
    0.08
    ç½ij
    0.08
    åŁł
    0.08
     networks
    0.07
    ous
    0.07
    ä¾Ľè¡Ģ
    0.07
     sanguÃŃ
    0.07
    網
    0.07
    絡
    0.07
    Activations Density 0.089%

    No Known Activations