© 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. 56735
    Prev
    Next
    INDEX
    Explanations

    exponential growth

    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
    缸åħ³çļĦ
    -0.08
    æľīåħ³çļĦ
    -0.08
    æŦ
    -0.07
    主è¦ģçļĦ
    -0.07
    åIJį为
    -0.07
    çļĦä¸Ģéĥ¨åĪĨ
    -0.07
     Dan
    -0.06
    ä»·çļĦ
    -0.06
    ense
    -0.06
    æŃ»äº¡çļĦ
    -0.06
    POSITIVE LOGITS
    ä½łåij¢
    0.08
    ä»ĸ们è¿ĺ
    0.08
    æ¯ıä¸Ģ个人
    0.07
    åĮĸåıijå±ķ
    0.07
    åĪĻåı¯
    0.07
    å¦Ĥæŀľä»ĸ们
    0.07
    èĢĮçĶŁ
    0.07
    èĢĮåĬ¨
    0.07
    æĢ§åĴĮ
    0.07
    iking
    0.07
    Activations Density 0.013%

    No Known Activations