© 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. 26750
    Prev
    Next
    INDEX
    Explanations

    divergence and logarithmic terms

    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
    ponder
    -0.07
    cip
    -0.07
    cipher
    -0.07
    ä¸īå®Ŀ
    -0.07
    ä¸İ管çIJĨ
    -0.07
    çķª
    -0.07
    ç«ĭæ¡Ī
    -0.07
    iar
    -0.06
    ohl
    -0.06
    .selectedIndex
    -0.06
    POSITIVE LOGITS
    à¦Ĺà§įর
    0.08
    褪
    0.08
    æĭīå°Ķ
    0.07
    .createComponent
    0.07
    ä¸Ŀ
    0.07
     plag
    0.07
    idity
    0.07
    ä¹ĺçĿĢ
    0.07
    iras
    0.07
    à¹ģà¸Ĺ
    0.06
    Activations Density 0.001%

    No Known Activations