© 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. 28458
    Prev
    Next
    INDEX
    Explanations

    mathematical statistics methods and computational modelling

    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
    è°ĥæį¢
    -0.08
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.07
     slight
    -0.07
    åĶı
    -0.07
    æĸ°çĶŁæ´»
    -0.07
    æĮīä¸ĭ
    -0.07
    ä¸Ģä¸ªäººåľ¨
    -0.07
    à°Ĺà±ģ
    -0.07
    arder
    -0.07
    èĩ³å°Ĭ
    -0.07
    POSITIVE LOGITS
     mathematical
    0.11
     applied
    0.11
     tools
    0.10
    Applied
    0.09
    /math
    0.09
     mathematics
    0.09
    è¿ĻéŨ
    0.09
    æķ°åѦ
    0.09
    æ±Ĥ解
    0.09
     Mathematical
    0.09
    Activations Density 0.249%

    No Known Activations