© 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. 38944
    Prev
    Next
    INDEX
    Explanations

    mathematical notation subunits

    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
    tee
    -0.06
    åĽŀ头çľĭ
    -0.06
    ç¿ģ
    -0.06
    ç©¿è¿ĩ
    -0.06
    设计
    -0.06
    perf
    -0.06
    ↵↵
    -0.06
     Lomba
    -0.05
    FR
    -0.05
    éĥİ
    -0.05
    POSITIVE LOGITS
    ljan
    0.08
    mÉĻk
    0.08
    æĶ¶ä¸ĭ
    0.08
     Protec
    0.08
    æĶ¾æ°´
    0.08
    crap
    0.08
     grosses
    0.08
    usión
    0.07
    èĴIJ
    0.07
     Descrição
    0.07
    Activations Density 0.003%

    No Known Activations