© 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. 22280
    Prev
    Next
    INDEX
    Explanations

    markup start sequence

    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
    гава
    -0.07
    entry
    -0.07
    reira
    -0.07
    /cs
    -0.07
    ourcem
    -0.07
    åĪ¶å®ļåĩº
    -0.07
    waan
    -0.07
    ural
    -0.06
    és
    -0.06
    poon
    -0.06
    POSITIVE LOGITS
    !--
    0.08
    ophys
    0.07
    à¯ģà®ķ
    0.07
    bü
    0.07
    缴éĢļ
    0.07
    agini
    0.07
    ihe
    0.07
    ä»Ģä¹ĪæĦıæĢĿ
    0.07
    big
    0.07
    ↵
    0.07
    Activations Density 0.193%

    No Known Activations