© 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. 11857
    Prev
    Next
    INDEX
    Explanations

    electron acceleration and radio frequency

    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
    æĶĺ
    -0.07
     desem
    -0.07
    é«ĺæ°Ķ
    -0.07
    èĮĥåĽ´å¹¿
    -0.07
     prox
    -0.07
    æİĴéĻ¤
    -0.07
    æ½Ń
    -0.06
    inei
    -0.06
    omi
    -0.06
    essler
    -0.06
    POSITIVE LOGITS
     synchronization
    0.10
     sincron
    0.08
     synchron
    0.08
     successive
    0.08
     synchronize
    0.08
    ynchronization
    0.08
     sync
    0.08
    åIJĮæŃ¥
    0.08
    ertz
    0.07
     progres
    0.07
    Activations Density 0.002%

    No Known Activations