© 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. 39516
    Prev
    Next
    INDEX
    Explanations

    applying math or science concepts

    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
    éĺħè¯»æľ¬æĸĩåīį
    -0.09
    代ä¹ĭ
    -0.08
    omet
    -0.08
    èĩ
    -0.07
    æľĢæĸ°ç«łèĬĤ
    -0.07
    WER
    -0.07
    ÄĻcz
    -0.07
    åħ±åĴĮåľĭ
    -0.07
    Ĺı
    -0.07
    éĢļè¿ĩåIJĦç§į
    -0.07
    POSITIVE LOGITS
     principles
    0.08
    à¸ŀระราà¸Ĭ
    0.07
    otal
    0.07
     Held
    0.07
    æīĢåŃ¦çŁ¥è¯Ĩ
    0.06
     generalized
    0.06
     Champ
    0.06
     principle
    0.06
     Item
    0.06
     virtue
    0.06
    Activations Density 0.039%

    No Known Activations