© 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. 22257
    Prev
    Next
    INDEX
    Explanations

    continued again

    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
     alone
    -0.07
    __$
    -0.07
    æĭīå¼ĢäºĨ
    -0.07
    ä¸Ģç½ij
    -0.07
    normally
    -0.07
    alone
    -0.06
    qus
    -0.06
     Mange
    -0.06
    å°±ä½į
    -0.06
     McCorm
    -0.06
    POSITIVE LOGITS
    继ç»Ń
    0.09
    ä»Ĭ度ãģ¯
    0.08
    åľ¨æĸ°çļĦ
    0.08
    ä¼ļ继ç»Ń
    0.08
     continued
    0.08
    ç¹¼çºĮ
    0.08
    åı¯ä»¥ç»§ç»Ń
    0.08
    anson
    0.08
     tục
    0.08
     after
    0.07
    Activations Density 0.232%

    No Known Activations