© 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. 20446
    Prev
    Next
    INDEX
    Explanations

    array, list, or combinations

    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
    ianza
    -0.07
    retta
    -0.07
    eszt
    -0.07
    ãĥ¼ãĤ¸ãĥ¼
    -0.07
    fors
    -0.07
     Seger
    -0.07
    .mybatis
    -0.07
    ellow
    -0.07
    ricia
    -0.07
    åĬ¡
    -0.07
    POSITIVE LOGITS
    ä¹Łåı¯ä»¥æĺ¯
    0.07
    á»ijng
    0.07
    ÙĨاد
    0.07
    _NONE
    0.07
    å¸ĥä»Ģ
    0.07
     Corse
    0.07
     combinations
    0.06
     combination
    0.06
    binations
    0.06
    常
    0.06
    Activations Density 0.112%

    No Known Activations