© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14750
    Prev
    Next
    INDEX
    Explanations

    OpenBSD, TOSHIBA, Spotify

    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
    åIJŁ
    -0.08
     hover
    -0.08
    æ¼Ĥ
    -0.07
    éĻIJ度
    -0.07
    æľ¦
    -0.07
    éĴĪ对
    -0.07
     expiration
    -0.07
    ãģ¥
    -0.06
     calculated
    -0.06
    åıįåIJij
    -0.06
    POSITIVE LOGITS
    -runner
    0.08
    æİĴåIJį第äºĮ
    0.08
    isky
    0.07
    muz
    0.07
    容纳
    0.07
     amalg
    0.07
     compact
    0.07
    _APPS
    0.07
    stype
    0.07
     configurations
    0.07
    Activations Density 0.019%

    No Known Activations