© 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. 22711
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    ÙĨب
    -0.08
    ัà¸Ļà¸Ĺ
    -0.07
    ç¬
    -0.07
    egot
    -0.07
    åĢ
    -0.06
    å¤ĦçIJĨèĥ½åĬĽ
    -0.06
    xCA
    -0.06
    uels
    -0.06
    å¤ļåIJĥä¸ĢäºĽ
    -0.06
     Chambers
    -0.06
    POSITIVE LOGITS
    缸åIJĮçļĦ
    0.07
    ä¸įæľ½
    0.07
    ιον
    0.07
    \base
    0.07
    atch
    0.07
     ÑģÑĤо
    0.07
    åĴĮå½±åĵį
    0.07
    åįĥåįĥä¸ĩ
    0.06
    iloc
    0.06
     same
    0.06
    Activations Density 0.147%

    No Known Activations