© 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. 40990
    Prev
    Next
    INDEX
    Explanations

    do + verb

    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
    aglio
    -0.09
    ingham
    -0.09
    ÛĮÚº
    -0.08
    ä¸Ģå¼łå¼ł
    -0.08
    áĥ§
    -0.08
    .gnu
    -0.08
    mong
    -0.08
    atici
    -0.08
    arif
    -0.08
    bildung
    -0.08
    POSITIVE LOGITS
    cket
    0.09
    ze
    0.08
    xygen
    0.08
    ä¹ĭ以
    0.07
    it
    0.07
     wonders
    0.07
    uate
    0.07
    å°±æĺ¯æĬĬ
    0.07
    il
    0.07
    کرد
    0.07
    Activations Density 0.255%

    No Known Activations