© 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. 33025
    Prev
    Next
    INDEX
    Explanations

    setup times, leakage, fittings

    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
    /gallery
    -0.08
    ÑģÑĤÑĢом
    -0.08
    yll
    -0.08
    çݺ
    -0.08
     Ore
    -0.08
    ront
    -0.08
    ç¬ĥ
    -0.07
    plet
    -0.07
     doGet
    -0.07
    endet
    -0.07
    POSITIVE LOGITS
     miscellaneous
    0.08
    éĻĦåĬł
    0.08
    è¶ģ
    0.07
    ousse
    0.07
    æĢ»è®¡
    0.07
    é¢Ŀå¤ĸ
    0.07
    åIJĦ
    0.07
     negligible
    0.07
    å®ļé¢Ŀ
    0.07
     additional
    0.07
    Activations Density 0.002%

    No Known Activations