© 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. 56329
    Prev
    Next
    INDEX
    Explanations

    code comments and programming keywords

    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
    -addon
    -0.08
    umblr
    -0.08
    auta
    -0.08
    æĸ°æĿij
    -0.08
    ÑħÑĢо
    -0.08
    []{
    -0.08
    é«ĺæ¡¥
    -0.08
    auge
    -0.08
    巨人
    -0.08
    },'
    -0.08
    POSITIVE LOGITS
    _parameter
    0.06
    0.06
    ness
    0.06
    inas
    0.06
    åį°
    0.06
    å¿ĻçļĦ
    0.06
     necessary
    0.06
    éĸij
    0.06
    æľ¬èģĮå·¥ä½ľ
    0.05
    ł
    0.05
    Activations Density 0.100%

    No Known Activations