© 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. 22807
    Prev
    Next
    INDEX
    Explanations

    importing class or continuous function

    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
     inciso
    -0.07
    Whilst
    -0.07
     ActionTypes
    -0.06
    ikko
    -0.06
    é¡·
    -0.06
    =='
    -0.06
     sogenannten
    -0.06
    uintptr
    -0.06
     cóm
    -0.06
    .hasOwnProperty
    -0.06
    POSITIVE LOGITS
    åı¯æĥ³èĢĮçŁ¥
    0.07
    agli
    0.07
     ols
    0.07
    çľĭåĪ°è¿Ļ
    0.07
    holt
    0.07
    解éĩĬ说
    0.06
    åĿĩéľĢ
    0.06
     treb
    0.06
    istere
    0.06
    åŃ¦ä¹łä¸İ
    0.06
    Activations Density 0.024%

    No Known Activations