© 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. 22107
    Prev
    Next
    INDEX
    Explanations

    python division and math operations

    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
    èĢĮåıijçĶŁ
    -0.08
    veno
    -0.08
    èĢĮå°±
    -0.08
    عار
    -0.08
    åħļæĢ»æĶ¯ä¹¦è®°
    -0.07
    æĬľãģij
    -0.07
    è¿ĿèĥĮ
    -0.07
     neither
    -0.07
    yarat
    -0.07
    ingly
    -0.07
    POSITIVE LOGITS
    æ··
    0.07
    arga
    0.06
    精确
    0.06
     precision
    0.06
    åķĨ
    0.06
    Úº
    0.06
     tunes
    0.06
    ola
    0.06
    chunk
    0.06
    æ··åIJĪ
    0.06
    Activations Density 0.003%

    No Known Activations