© 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. 20947
    Prev
    Next
    INDEX
    Explanations

    print with arguments

    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
    大åĪ©
    -0.08
    uron
    -0.07
     [[]
    -0.07
    ibera
    -0.07
    ippo
    -0.07
    宦
    -0.07
    kaus
    -0.07
    ÏĦά
    -0.07
    нин
    -0.07
    zen
    -0.07
    POSITIVE LOGITS
    çĶ·å¥³
    0.11
     ëĤ¨ëħĢ
    0.09
     ÙħجÙħÙĪع
    0.08
    æĢ»
    0.08
     pairs
    0.08
    ä¸ī人
    0.08
    åħĦ妹
    0.08
    çĶ²ä¹ĻåıĮæĸ¹
    0.07
    两边çļĦ
    0.07
     pair
    0.07
    Activations Density 0.003%

    No Known Activations