© 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. 57710
    Prev
    Next
    INDEX
    Explanations

    ordinarily, normally, naturally

    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
    ίÏĥ
    -0.08
    orde
    -0.08
    esai
    -0.08
    ENA
    -0.08
    æľĢæľĢ
    -0.08
    天ä¸Ĭ
    -0.07
    ç«Łæĺ¯
    -0.07
     vergelijk
    -0.07
    åĥıåľ¨
    -0.07
    quel
    -0.07
    POSITIVE LOGITS
    æľīåĪ«
    0.08
     naturally
    0.07
    æīįæľī
    0.07
    ä½ķ
    0.07
    atre
    0.07
     ordinarily
    0.06
     normally
    0.06
     عادة
    0.06
    æľīä¸įåIJĮ
    0.06
    ÑĢож
    0.06
    Activations Density 0.088%

    No Known Activations