© 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. 38194
    Prev
    Next
    INDEX
    Explanations

    formulaic mathematical principles

    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
     Tutt
    -0.08
    è°ľ
    -0.07
    lå
    -0.07
    æĪijçļĦ书æŀ¶
    -0.07
    æĮ£æīİ
    -0.07
    éĺ³æĺ¥
    -0.07
    izzi
    -0.07
    elan
    -0.07
    URING
    -0.07
    æł¸åĩĨæĹ¥æľŁ
    -0.07
    POSITIVE LOGITS
     fundamentals
    0.06
    gada
    0.06
    çļĦç»ıåħ¸
    0.06
    Sequential
    0.06
    asier
    0.06
    æľĢåŁºæľ¬
    0.06
    gos
    0.06
    aud
    0.06
    æľĢç¾İ好çļĦ
    0.06
    å®Ŀå¡Ķ
    0.05
    Activations Density 0.052%

    No Known Activations