© 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. 8930
    Prev
    Next
    INDEX
    Explanations

    bitwise complement, volatile memories, manhattan distance, sorted integer arrays

    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
     sema
    -0.09
    umul
    -0.08
    ridor
    -0.08
    à¦ŀà§įà¦ľ
    -0.07
    大å¢ŀ
    -0.07
    ÏħÏĩ
    -0.07
    æĪij第ä¸Ģ次
    -0.07
    çİĭæ°ı
    -0.07
    ÑĪелÑĮ
    -0.07
    idget
    -0.07
    POSITIVE LOGITS
    Âł
    0.07
    egers
    0.07
    orr
    0.06
    1
    0.06
    è°¢æĦı
    0.06
    /reference
    0.06
    ç¨ĭåºı设计
    0.06
    oczy
    0.05
     опеÑĢ
    0.05
     lint
    0.05
    Activations Density 0.025%

    No Known Activations