© 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. 33539
    Prev
    Next
    INDEX
    Explanations

    sorting and ranking lists

    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
    amet
    -0.08
    lotte
    -0.07
    ehler
    -0.07
    ë²Ķ
    -0.07
    impan
    -0.07
    ק×Ķ
    -0.07
    è¨Ģä¼ł
    -0.07
    _vlog
    -0.07
    ×ķ×ķ
    -0.07
    abb
    -0.06
    POSITIVE LOGITS
    æİĴåºı
    0.10
     sort
    0.09
     sorted
    0.09
     sortable
    0.09
    _sort
    0.09
     sorting
    0.09
    .argsort
    0.09
    æĺ¯æĮī
    0.08
    Sort
    0.08
    å§ĵ
    0.08
    Activations Density 0.044%

    No Known Activations