© 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. 62639
    Prev
    Next
    INDEX
    Explanations

    counter and accumulate

    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
    å´Ń
    -0.08
    å±±éķĩ
    -0.08
    æ¯Ķèĩªå·±
    -0.08
    à¸Ĥัà¸Ļ
    -0.07
    ÙĦÙĪ
    -0.07
    æĤį
    -0.07
    èĩªåı¤
    -0.07
    usza
    -0.07
    缸æĴŀ
    -0.07
    /ge
    -0.07
    POSITIVE LOGITS
    累计
    0.12
    ç´¯
    0.10
     cumulative
    0.09
     Cum
    0.09
    æ¯ı次
    0.09
    累积
    0.08
     accum
    0.08
    cum
    0.08
     accumulate
    0.08
    Cum
    0.08
    Activations Density 0.069%

    No Known Activations