© 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. 57294
    Prev
    Next
    INDEX
    Explanations

    present invention

    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
    ophage
    -0.07
     normalize
    -0.07
    Normalization
    -0.07
     Bima
    -0.07
     tapered
    -0.07
     incidente
    -0.07
    ëŁīìĿĦ
    -0.07
    æĬĸåĬ¨
    -0.07
    éĽĨä¸Ń度
    -0.07
    ÑĪно
    -0.07
    POSITIVE LOGITS
     spont
    0.10
    åľ¨é«ĺ温
    0.08
     temperature
    0.08
     Temperature
    0.08
    temperature
    0.07
     (-
    0.07
    驱åĬ¨åĬĽ
    0.07
    æİĴ忧解éļ¾
    0.07
     combination
    0.07
    abi
    0.07
    Activations Density 0.003%

    No Known Activations