© 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. 55819
    Prev
    Next
    INDEX
    Explanations

    function definition or programming constructs

    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
    ä¸įæĸŃ丰å¯Į
    -0.07
    ud
    -0.07
    ople
    -0.07
    éĴ°
    -0.07
    art
    -0.06
    éĽ
    -0.06
     heels
    -0.06
     bundles
    -0.06
    comfort
    -0.06
     mand
    -0.06
    POSITIVE LOGITS
    åºĶçĶ¨åĪ°
    0.10
    Applied
    0.10
     applied
    0.09
    ä¹ĺ以
    0.09
     Applied
    0.09
    对åѦçĶŁçļĦ
    0.09
    ä½ľçĶ¨ä¸ĭ
    0.09
    è¿IJçĶ¨åĪ°
    0.09
     multiply
    0.08
    รัมยà¹Į
    0.08
    Activations Density 0.147%

    No Known Activations