© 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. 62983
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and indices

    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
    飬
    -0.07
    ål
    -0.07
    该车
    -0.07
    该è¡Į
    -0.07
    abet
    -0.06
    éĵ¿
    -0.06
    xdd
    -0.06
    dfa
    -0.06
    è±Ĩ
    -0.06
    /tab
    -0.06
    POSITIVE LOGITS
    ä¸Ńå¿ĥ
    0.08
    CENTER
    0.07
    ä¸Ģè§ģ
    0.07
    HOR
    0.07
    _patches
    0.07
    webdriver
    0.07
    éķľ
    0.06
    ä¸Ńå¿ĥçŃī
    0.06
    æĹ¥æľĪ
    0.06
    gregar
    0.06
    Activations Density 0.003%

    No Known Activations