© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22091
    Prev
    Next
    INDEX
    Explanations

    provided or preview

    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
     somewhat
    -0.08
     seeming
    -0.07
    "
    -0.07
     "\(
    -0.06
     Interestingly
    -0.06
    交代
    -0.06
    (?)
    -0.06
    æķĻç§ij书
    -0.06
    ç»Ļå®ĥ
    -0.06
     Dixon
    -0.06
    POSITIVE LOGITS
    天ä¸Ģ
    0.09
    以ä¸ĭæĺ¯å°ıç¼ĸ
    0.08
    ä»ĬæĹ¥çļĦ
    0.08
    æ¯ıä½į
    0.08
    åĪª
    0.08
     ä»ĬæĹ¥
    0.08
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.07
    åĪĨæŀIJåıĬ
    0.07
     preview
    0.07
    (__
    0.07
    Activations Density 0.007%

    No Known Activations