© 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. 46636
    Prev
    Next
    INDEX
    Explanations

    programming method names

    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
    cope
    -0.07
    ç´Ķ
    -0.07
    owie
    -0.07
    cov
    -0.07
    OBO
    -0.07
    ropp
    -0.07
    .spi
    -0.07
    pure
    -0.07
    æĽ´åı¯
    -0.07
    ():
    -0.06
    POSITIVE LOGITS
    äºĮåŃĹ
    0.08
    è¿Ļ个è¯į
    0.07
    è¿Ļ个éģĵçIJĨ
    0.06
    راÙħ
    0.06
    ze
    0.06
    getElement
    0.06
    ä¸Ģè¯į
    0.06
     PRESID
    0.06
    åĨįæİ¥
    0.06
    åĪ«çľĭ
    0.06
    Activations Density 0.006%

    No Known Activations