© 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. 50631
    Prev
    Next
    INDEX
    Explanations

    deriving mathematical formulas

    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
    anova
    -0.07
    æĪijç»Ļ
    -0.06
    åıĹåĩī
    -0.06
    ienze
    -0.06
     recent
    -0.06
    åĩĨå¤ĩ好çļĦ
    -0.06
    enate
    -0.06
    asso
    -0.06
     Plans
    -0.06
    iloc
    -0.06
    POSITIVE LOGITS
    çļĦä¸ĢèĪ¬
    0.08
     derivation
    0.08
    秫
    0.07
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    0.07
    éĻIJ度çļĦ
    0.07
     جدÙĬدة
    0.07
     expressing
    0.07
    并æľĢç»Ī
    0.07
    æĥħåĨµåIJİ
    0.07
    缸åħ³æ³ķå¾ĭ责任
    0.07
    Activations Density 0.031%

    No Known Activations