© 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. 12866
    Prev
    Next
    INDEX
    Explanations

    function arguments or variables

    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
    ülü
    -0.07
    buster
    -0.07
    ÏĦÏģÏĮ
    -0.07
     Titolo
    -0.07
    orts
    -0.07
    æijĺä¸ĭ
    -0.07
    IMATE
    -0.06
    KNOWN
    -0.06
    丼
    -0.06
    무
    -0.06
    POSITIVE LOGITS
    .native
    0.08
    lij
    0.07
    宫ä¸Ń
    0.07
    leo
    0.07
    leih
    0.06
    ichen
    0.06
    arias
    0.06
    æĸĩ稿
    0.06
    lik
    0.06
    ç³
    0.06
    Activations Density 0.010%

    No Known Activations