© 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. 63244
    Prev
    Next
    INDEX
    Explanations

    party names or abbreviations

    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
    深深çļĦ
    -0.07
    æĹłæĦ§
    -0.07
    orro
    -0.07
    深深
    -0.07
     prer
    -0.06
    eck
    -0.06
    arro
    -0.06
    æłijä¸ĬçļĦ
    -0.06
    æ·±æ·±åľ°
    -0.06
     Cano
    -0.06
    POSITIVE LOGITS
    éķľåĥı
    0.08
     thirds
    0.07
    cheng
    0.07
    ä¹Łæĺ¯å¦ĤæѤ
    0.07
    ecedor
    0.07
    ä¹Łæĺ¯ä¸Ģæł·
    0.07
     batchSize
    0.07
    ä¹Łä¸Ģæł·
    0.07
    pNet
    0.07
     неплоÑħо
    0.07
    Activations Density 0.003%

    No Known Activations