© 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. 24826
    Prev
    Next
    INDEX
    Explanations

    modification or complexity

    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
     rê
    -0.08
    åIJĮåIJį
    -0.08
    æĹłåıį
    -0.08
    NotFoundError
    -0.07
    afia
    -0.07
    clin
    -0.07
    åĨ°ç³ĸ
    -0.07
    Fatal
    -0.07
    ../../../../
    -0.07
    çµIJ
    -0.07
    POSITIVE LOGITS
     complexity
    0.08
    å¤įæĿĤæĢ§
    0.08
    èĩ³å°ij
    0.08
     Complexity
    0.08
    å°±ä¸įåĨį
    0.07
    complex
    0.07
    å¤įæĿĤ
    0.07
     almeno
    0.07
    æ¿Ģæ´»
    0.07
    æ·Ĩ
    0.07
    Activations Density 0.082%

    No Known Activations