© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30178
    Prev
    Next
    INDEX
    Explanations

    arithmetic or code identifiers

    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
    ä¸ĩå¹´
    -0.07
    ä¸ĩåıª
    -0.07
    <![
    -0.07
    æľīçļĦåIJĮåѦ
    -0.07
    amik
    -0.07
    uest
    -0.07
    ķ
    -0.07
    áŀ¶áŀĢáŁĭ
    -0.07
    åģ¶
    -0.07
    ä¼ļåIJĮ
    -0.07
    POSITIVE LOGITS
    åij¼åIJ¸
    0.06
     goodies
    0.06
    èĢģæĮĿ
    0.06
    ican
    0.06
    ÙĦÙĥ
    0.06
    éĤ£ä¸ĢåĪ»
    0.06
    enet
    0.06
    容è²Į
    0.06
    niest
    0.06
    issan
    0.06
    Activations Density 0.004%

    No Known Activations