© 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. 30103
    Prev
    Next
    INDEX
    Explanations

    foliation, normally, ordinarily

    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
    aland
    -0.07
     Pee
    -0.07
    æľīèĩ´
    -0.07
    IRT
    -0.07
    ä¸įä¸Ģ
    -0.06
    zinho
    -0.06
    uppet
    -0.06
    rapper
    -0.06
    ª
    -0.06
    è³¢
    -0.06
    POSITIVE LOGITS
    à¸Ńยูà¹Īà¹ģลà¹īว
    0.11
     normally
    0.10
    æľ¬å°±
    0.09
     ordinarily
    0.08
    æľ¬æĿ¥å°±æĺ¯
    0.08
     zaten
    0.08
    æľ¬æĿ¥å°±
    0.08
    æľ¬èº«å°±æĺ¯
    0.08
    æľ¬èº«å°±
    0.08
    normally
    0.08
    Activations Density 0.495%

    No Known Activations