© 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. 47372
    Prev
    Next
    INDEX
    Explanations

    fatigue processes

    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
    liness
    -0.09
    ÙĬÙĨ
    -0.08
    mits
    -0.08
    zinho
    -0.08
     кÑĢай
    -0.08
    åį³æĹ¥èµ·
    -0.07
    æ¼ĶçļĦ
    -0.07
     fizi
    -0.07
    edly
    -0.07
    -purpose
    -0.07
    POSITIVE LOGITS
    两åѦä¸Ģåģļ
    0.07
    æĢģ
    0.07
    å¯ŀ
    0.06
    åľ¨èº«
    0.06
    áĢIJáĢº
    0.06
    ESSO
    0.06
    ddb
    0.06
    urn
    0.06
     пÑĢоÑģмо
    0.06
    æľŁéĻIJåĨħ
    0.06
    Activations Density 0.003%

    No Known Activations