© 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. 40278
    Prev
    Next
    INDEX
    Explanations

    polytope, polynomial, or represented

    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
    æµĴ
    -0.10
    æİĸ
    -0.09
    ä¾łä¼ł
    -0.08
    /proto
    -0.08
    ÑĤÑĢанÑģпоÑĢÑĤ
    -0.08
    å²Ĺä½įèģĮè´£
    -0.08
    æĹ¥æĸ°æľĪ
    -0.08
    rust
    -0.08
    InstanceState
    -0.08
    é¾Ļæ³ī
    -0.08
    POSITIVE LOGITS
     pers
    0.08
     pac
    0.08
     uniform
    0.08
    åĿĩåĮĢ
    0.07
     group
    0.07
    åĿĩåĮĢçļĦ
    0.07
    éĥ¨èIJ½
    0.07
     soci
    0.07
    èģļ
    0.07
    åħ±äº«
    0.07
    Activations Density 0.004%

    No Known Activations