© 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. 41032
    Prev
    Next
    INDEX
    Explanations

    examples or list items

    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
    åľ¨éĺħ读
    -0.07
    ierta
    -0.07
    dain
    -0.07
    åľ¨æŀĹ
    -0.07
    alj
    -0.07
    teur
    -0.07
    常ä½ı人åı£
    -0.07
    ä½ľåĪĻ
    -0.07
    lobal
    -0.06
    alisi
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.11
     halnya
    0.11
    ä¸įéĻIJäºİ
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    éĢļè¿ĩ
    0.08
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.08
    以ä¸ĭåĩłç§į
    0.08
     appunto
    0.08
    à¹Ģà¸Ķียวà¸ģัà¸Ļ
    0.08
     اÛĮÙĨÚ©Ùĩ
    0.07
    Activations Density 0.004%

    No Known Activations