© 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. 18686
    Prev
    Next
    INDEX
    Explanations

    explain or suggest

    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
    à¸Ńยูà¹Īà¹ģลà¹īว
    -0.07
    orgen
    -0.07
    ÚĺÙĩ
    -0.07
    ÑģÑĬ
    -0.07
    å·´å¡ŀ
    -0.06
    .PNG
    -0.06
    ziale
    -0.06
    áĢĦáĢºáĢ¸
    -0.06
    LEASE
    -0.06
    åħ»æĪIJäºĨ
    -0.06
    POSITIVE LOGITS
    è¡Įä¹ĭ
    0.09
    ä¸ĭåIJĮ
    0.07
    æģ°å½ĵ
    0.07
    ito
    0.06
    符åIJĪè¦ģæ±Ĥ
    0.06
    ary
    0.06
    oh
    0.06
    гла
    0.06
    umb
    0.06
    arily
    0.06
    Activations Density 0.028%

    No Known Activations