© 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. 23425
    Prev
    Next
    INDEX
    Explanations

    mathematical expression resolution

    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
    æ·±åħ¥æµħ
    -0.08
    azi
    -0.07
    acas
    -0.07
    åħ¶å®ĥåªĴä½ĵ
    -0.07
    ש×ķ
    -0.07
    =-=-=-=-=-=-=-=-
    -0.07
    оеди
    -0.07
    éĿĴ涩
    -0.07
    çݯä¿ĿæĦıè¯Ĩ
    -0.06
    jeros
    -0.06
    POSITIVE LOGITS
    ç§ĭæľĪ
    0.08
    ä¸Ģæ»´
    0.08
    æĹłåı¯
    0.07
    度
    0.07
     molest
    0.06
    å¦ĥ
    0.06
    åıª
    0.06
    æĽ³
    0.06
    degree
    0.06
    ä¸Ģ票
    0.06
    Activations Density 0.013%

    No Known Activations