© 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. 24552
    Prev
    Next
    INDEX
    Explanations

    training data and models

    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
    éĮ¯
    -0.07
    ä¸Ģä¸Ŀ
    -0.07
     زÛĮب
    -0.07
    perc
    -0.06
    iola
    -0.06
    æŁı
    -0.06
     brutto
    -0.06
    ä¸įæĢ¥
    -0.06
    Scheduled
    -0.06
    ìĿ¼ë³´
    -0.06
    POSITIVE LOGITS
    (training
    0.09
    éĽĨä¸ŃåŃ¦ä¹ł
    0.08
    è®Ńç»ĥ
    0.08
     training
    0.08
     biases
    0.08
    æ±Ģ
    0.08
    czyn
    0.08
    è®Ńç»ĥçļĦ
    0.08
    éĶ¤çĤ¼
    0.08
    æł·æľ¬
    0.08
    Activations Density 0.068%

    No Known Activations