© 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. 17132
    Prev
    Next
    INDEX
    Explanations

    date range separators

    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
    ELLO
    -0.08
    Ïģγ
    -0.08
    ã
    -0.07
    壤
    -0.07
    ETTO
    -0.07
    oha
    -0.07
    å®ĺåı¸
    -0.07
    äºĭåIJİ
    -0.06
    eron
    -0.06
    ót
    -0.06
    POSITIVE LOGITS
    Invoker
    0.08
    æİĴæĶ¾æłĩåĩĨ
    0.07
    IBC
    0.07
    urras
    0.07
    ä¸Ĭä¸Ģå±Ĥ楼
    0.07
    为è¾ħ
    0.07
    å¾Ģä¸ĭ
    0.07
    {}\
    0.07
    letcher
    0.07
    emale
    0.07
    Activations Density 0.038%

    No Known Activations