© 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. 13749
    Prev
    Next
    INDEX
    Explanations

    from import paths

    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
    azin
    -0.08
    iby
    -0.08
    ulik
    -0.07
    Ùħرت
    -0.07
    orz
    -0.07
    /logs
    -0.07
     #[
    -0.07
    æĿ¡ä»¶æĺ¯
    -0.07
    ׼×Ķ
    -0.07
    erness
    -0.07
    POSITIVE LOGITS
     '
    0.08
    chie
    0.07
     './
    0.07
    sher
    0.07
     "
    0.07
    _blocking
    0.06
    .;
    0.06
    ëĭ¬
    0.06
     "./
    0.06
    å¼ı
    0.06
    Activations Density 0.037%

    No Known Activations