© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 24564
    Prev
    Next
    INDEX
    Explanations

    car brands like Honda

    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
    éĻ¢çļĦ
    -0.07
    ä¸Ģå°ģ
    -0.07
    allis
    -0.06
    åĨ²åĨ²
    -0.06
    éĻ¢æīĢ
    -0.06
    çļĦç¡®æĺ¯
    -0.06
    olio
    -0.06
     ctor
    -0.06
    _names
    -0.06
    ä¸ĢæĭĽ
    -0.06
    POSITIVE LOGITS
    ç³»
    0.09
    çīĪæĿĥä¸İåħį责声æĺİ
    0.07
    enni
    0.07
    askan
    0.07
    Legend
    0.07
    aison
    0.07
    太强
    0.07
    antine
    0.06
     versatile
    0.06
    _BEGIN
    0.06
    Activations Density 0.037%

    No Known Activations