© 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. 14951
    Prev
    Next
    INDEX
    Explanations

    options, buttons, chosen, candidates

    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
     Mand
    -0.07
    迹
    -0.07
    np
    -0.07
    è¸ıè¸ıå®ŀ
    -0.06
     traced
    -0.06
    é¡·åĪ»
    -0.06
     Gover
    -0.06
    å°ıäºĮ
    -0.06
    快讯
    -0.06
    epis
    -0.06
    POSITIVE LOGITS
    åı¯ä¾ĽéĢīæĭ©
    0.09
    ç«ŀäºīçļĦ
    0.09
    éĢī项
    0.08
     offerings
    0.08
    à¹ĥหà¹īà¹Ģลืà¸Ńà¸ģ
    0.08
    æİĴåĪĹ
    0.08
    ç«ŀäºī
    0.08
     offered
    0.08
    å¥ĭæĸĹ缮æłĩ
    0.08
    à¸ķัวà¹Ģลืà¸Ńà¸ģ
    0.08
    Activations Density 0.023%

    No Known Activations