© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21749
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
     elements
    -0.07
    ä¸įæĪIJ
    -0.07
    Element
    -0.07
    临
    -0.07
    鬼
    -0.06
    æį§
    -0.06
    RT
    -0.06
    aba
    -0.06
    èİĺ
    -0.06
     associates
    -0.06
    POSITIVE LOGITS
    ringer
    0.08
    EDIA
    0.08
    pje
    0.08
    åľĨ满ç»ĵæĿŁ
    0.08
    าะ
    0.08
    ãĤ¦ãĥ³
    0.08
     Bạc
    0.08
    çļĦä¸Ģ款
    0.08
    oji
    0.08
    à¹Īาà¸Ļ
    0.07
    Activations Density 0.005%

    No Known Activations