© 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. 28857
    Prev
    Next
    INDEX
    Explanations

    button clicks

    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
    anner
    -0.09
    ĵĴ
    -0.09
    åı¤å±ĭ
    -0.08
    fran
    -0.08
    æľīæīĢæĢĿ
    -0.08
    URN
    -0.08
    ranc
    -0.08
    AndGet
    -0.08
    æĴŃåĩºçļĦ
    -0.08
    ãĤ¯ãĥģ
    -0.08
    POSITIVE LOGITS
    åĨį次
    0.15
    éĩįæĸ°
    0.15
     again
    0.15
    继ç»Ńè¿Ľè¡Į
    0.13
    éĩįæĸ°å¼Ģå§ĭ
    0.12
     Ñģнова
    0.12
     anew
    0.12
    again
    0.12
    æĸ°ä¸Ģè½®
    0.12
    æĸ°çļĦ
    0.12
    Activations Density 0.188%

    No Known Activations