© 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. 26681
    Prev
    Next
    INDEX
    Explanations

    sorting and algorithms

    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
    abila
    -0.08
    สิà¹īà¸Ļ
    -0.08
    祥
    -0.08
    åľ¨åĪ«äºº
    -0.07
    é¹Ń
    -0.07
    æĩ·
    -0.07
    å®īåħ¨é£İéĻ©
    -0.07
    æĢĢ
    -0.07
    pong
    -0.07
    trut
    -0.07
    POSITIVE LOGITS
    æİĴåºı
    0.10
    Sorting
    0.09
     sorting
    0.08
    sorted
    0.08
    sorting
    0.08
    (sort
    0.08
     Sorting
    0.08
     sorter
    0.07
    _sort
    0.07
    akedown
    0.07
    Activations Density 0.001%

    No Known Activations