© 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. 47370
    Prev
    Next
    INDEX
    Explanations

    light and oxygen regulation

    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
     çıkar
    -0.08
    ç¾¹
    -0.07
    à¸Ńม
    -0.07
     Festa
    -0.07
    ogi
    -0.07
    rol
    -0.07
    妥
    -0.07
    обÑĢ
    -0.07
    åħ°çī¹
    -0.07
    cript
    -0.07
    POSITIVE LOGITS
    æĻĴ
    0.07
    æĺİåªļ
    0.07
    æĺ¼å¤ľ
    0.07
    æĽĿ
    0.07
    phot
    0.07
    èĩªçĦ¶çķĮ
    0.07
    以å¤ĸçļĦ
    0.07
    light
    0.07
    çݯå¢ĥ
    0.07
     exposure
    0.07
    Activations Density 0.011%

    No Known Activations