© 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. 46844
    Prev
    Next
    INDEX
    Explanations

    Big O notation

    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
    åĽĬ
    -0.07
    æĸ½
    -0.06
    åºĶ该注æĦı
    -0.06
    ç¾İå¾Ĺ
    -0.06
    æĬĺ
    -0.06
    iraz
    -0.06
    ç¡
    -0.06
    mdl
    -0.06
    äºijéĽĨ
    -0.06
    æ²½
    -0.06
    POSITIVE LOGITS
    kaus
    0.09
    _once
    0.08
    ä¸Ģåİ»
    0.08
    å¤ļå°ij次
    0.08
    ä¸Ģè¶Ł
    0.08
    utri
    0.07
    .ForEach
    0.07
    æ´¾åıij
    0.07
    uations
    0.07
    级åĪ«çļĦ
    0.07
    Activations Density 0.004%

    No Known Activations