© 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. 30797
    Prev
    Next
    INDEX
    Explanations

    administrative divisions

    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
    åĮºå§Ķ书记
    -0.09
    åĮºäººæ°ijæĶ¿åºľ
    -0.08
    éķĩ人æ°ijæĶ¿åºľ
    -0.07
    åį«åģ¥å§Ķ
    -0.07
    åĮºæĶ¿åºľ
    -0.06
    ä¸ºæł¸å¿ĥçļĦåħļä¸Ń央
    -0.06
    arna
    -0.06
    æĵįå¿ĥ
    -0.06
    æŃ»åIJİ
    -0.06
    åİ¿å§Ķ常å§Ķ
    -0.06
    POSITIVE LOGITS
    egos
    0.08
     semiclass
    0.08
     деÑĤÑģÑĤва
    0.08
    çı¾æľī
    0.08
    µ¬
    0.07
     Shope
    0.07
    å²Ĺ
    0.07
    以ä¸Ĭå°±æĺ¯å°ıç¼ĸ
    0.07
    çĶ¨æĪ·ä½¿çĶ¨
    0.07
    æīĢå±ŀ
    0.07
    Activations Density 0.035%

    No Known Activations