© 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. 21832
    Prev
    Next
    INDEX
    Explanations

    file format conversion

    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
    lessness
    -0.07
    ä¸Ģéĥİ
    -0.07
    ä¸Ĭ线
    -0.07
    à¦¾à¦ľ
    -0.06
    elum
    -0.06
     senses
    -0.06
     HashSet
    -0.06
    ully
    -0.06
    uzzi
    -0.06
    çľĭä¸Ń
    -0.06
    POSITIVE LOGITS
     format
    0.14
    æł¼å¼ı
    0.14
    æł¼å¼ıçļĦ
    0.14
    -format
    0.13
     formats
    0.13
    format
    0.12
     Format
    0.12
    Format
    0.12
    æĸĩä»¶æł¼å¼ı
    0.11
    _format
    0.11
    Activations Density 0.345%

    No Known Activations