© 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. 9093
    Prev
    Next
    INDEX
    Explanations

    electric, hybrid, autonomous vehicles

    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
    ivet
    -0.08
    sey
    -0.07
    ç¯Ŀ
    -0.06
    æĸĽ
    -0.06
    çİīæłij
    -0.06
    еÑĩно
    -0.06
    è¯Ń
    -0.06
    æĸ°åĨľæĿij
    -0.06
    æĢ»èĥ½
    -0.06
     minimized
    -0.06
    POSITIVE LOGITS
    çŃīæĸ°
    0.09
    -ready
    0.09
     transition
    0.09
     dần
    0.09
    åħĥå¹´
    0.09
    ä¸İä¼łç»Ł
    0.09
     Transition
    0.08
    æĽ¿ä»£
    0.08
    .nodeType
    0.08
    _transition
    0.08
    Activations Density 0.219%

    No Known Activations