© 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. 39720
    Prev
    Next
    INDEX
    Explanations

    event and competition titles

    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
     billions
    -0.08
    èĩ£
    -0.08
     rigid
    -0.07
    ç½ijæł¡
    -0.07
    ä¼ļå±ķä¸Ńå¿ĥ
    -0.07
    åĬ¨ä¸įåĬ¨
    -0.06
    ä¸Ĭä¸ĭæĸĩ
    -0.06
    èij¬ç¤¼
    -0.06
    大åѦåѦæĬ¥
    -0.06
    å±ķè§Īä¼ļ
    -0.06
    POSITIVE LOGITS
    åĮºåĨħ
    0.09
    кÑĨиÑı
    0.08
    çī¹åĪ«çļĦ
    0.08
    å±ĬæŶ
    0.08
     themed
    0.08
    mini
    0.08
    æĿĪ
    0.08
     specially
    0.08
    è¼Ķ
    0.08
    éįĬ
    0.08
    Activations Density 1.692%

    No Known Activations