© 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. 26535
    Prev
    Next
    INDEX
    Explanations

    requires or needs

    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
    arily
    -0.10
    voud
    -0.10
    uary
    -0.10
    ìį¨
    -0.09
    °
    -0.09
    ently
    -0.09
    jenigen
    -0.09
    ustr
    -0.09
    ëĭ¤ë©´
    -0.09
    rou
    -0.08
    POSITIVE LOGITS
    ات
    0.13
    s
    0.10
    ãģĦãĤĭ
    0.09
    es
    0.08
    çī¹åĪ«æ³¨æĦı
    0.08
    ãģ£ãģįãĤĬ
    0.08
    ×Ļ×Ŀ
    0.08
    åĪ°å¤§
    0.07
    åģļçļĦå°±æĺ¯
    0.07
    注æĦıçļĦæĺ¯
    0.07
    Activations Density 0.001%

    No Known Activations