© 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. 26334
    Prev
    Next
    INDEX
    Explanations

    numbers and groups

    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
    ï¸ı
    -0.09
    erald
    -0.08
    ively
    -0.08
    ترÛĮÙĨ
    -0.07
    mert
    -0.07
    åĩłå£°
    -0.07
    lds
    -0.07
    åĴĮå®ĮåĸĦ
    -0.07
    wach
    -0.07
    ÑĤек
    -0.07
    POSITIVE LOGITS
    ä¹ĭä¸ĢçļĦ
    0.11
    æĪĸå¤ļ
    0.09
    fold
    0.09
    åĴĮä¸ī
    0.09
    æĪĸ以ä¸Ĭ
    0.09
    ä¹ĭé¦ĸ
    0.08
    otomy
    0.08
    çļĨ
    0.08
    çļĨæľī
    0.08
    ãģĨãģ¡
    0.08
    Activations Density 0.009%

    No Known Activations