© 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. 60803
    Prev
    Next
    INDEX
    Explanations

    OpenZipkin Authors

    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
    åµ
    -0.08
    |[
    -0.07
    versations
    -0.07
     |[
    -0.07
    anted
    -0.07
    æĪİ
    -0.07
    好
    -0.07
    attel
    -0.07
    otis
    -0.06
    lys
    -0.06
    POSITIVE LOGITS
    лÑij
    0.07
    åı°ä¸ĭ
    0.07
    enberg
    0.07
    à¸Ńุà¸ķ
    0.07
    META
    0.07
    fdc
    0.07
    orts
    0.06
    éĢļå·ŀ
    0.06
    å¼ĺ
    0.06
    GRAM
    0.06
    Activations Density 0.043%

    No Known Activations