© 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. 38238
    Prev
    Next
    INDEX
    Explanations

    for key, x

    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
    çķľ
    -0.07
    ä¸įèĥ½å®Įåħ¨
    -0.07
    æݧ
    -0.07
    angg
    -0.06
    uka
    -0.06
    alah
    -0.06
    æĻĴ
    -0.06
    ale
    -0.06
    rou
    -0.06
    orr
    -0.06
    POSITIVE LOGITS
    где
    0.07
    ymi
    0.07
     Cán
    0.07
    eby
    0.07
    ÑħÑĤа
    0.07
    ä¾µçĬ¯äºĨæĤ¨çļĦ
    0.07
    æĤ¶
    0.06
    antai
    0.06
     Powered
    0.06
    indices
    0.06
    Activations Density 0.017%

    No Known Activations