© 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. 16650
    Prev
    Next
    INDEX
    Explanations

    rms and peak tracking

    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
    èħ¹é»ij
    -0.08
    大马
    -0.08
     Shay
    -0.07
    stil
    -0.07
    åıĮåŃIJ座
    -0.07
    çļĦè·Ŀ离
    -0.07
    ÑĨей
    -0.07
    éªĮè¯ģçłģ
    -0.07
    -map
    -0.07
     accordion
    -0.07
    POSITIVE LOGITS
     equivalents
    0.09
    æīįå¹²
    0.08
    çŃīæķĪ
    0.07
    rms
    0.07
    æĬĺç®Ĺ
    0.07
    æĬĺåIJĪ
    0.07
    æ¯Ķåݻ年åIJĮæľŁ
    0.07
    èĬ±èĬ±
    0.07
    åĢ¼åĴĮ
    0.07
     equivalent
    0.07
    Activations Density 0.002%

    No Known Activations