© 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. 64365
    Prev
    Next
    INDEX
    Explanations

    small and medium businesses

    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
     muka
    -0.08
    使人
    -0.07
    PILE
    -0.07
    æĪ¿å¸Ĥ
    -0.07
    é«ĺä½į
    -0.07
    åѦçĶŁå¹²éĥ¨
    -0.07
    æľºæ¢°è®¾è®¡
    -0.07
    对人类
    -0.07
    严èĤĥå¤ĦçIJĨ
    -0.07
    ropp
    -0.07
    POSITIVE LOGITS
    åĢĴéĹŃ
    0.09
     SME
    0.09
    /small
    0.09
    è§Ħ模
    0.08
     artisan
    0.08
    è¦ı模
    0.08
    -owned
    0.08
    è¿ĻäºĽå°ı
    0.08
     малого
    0.08
     surviving
    0.08
    Activations Density 0.147%

    No Known Activations