© 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. 30772
    Prev
    Next
    INDEX
    Explanations

    equivalents and counterparts

    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
    θÎŃ
    -0.08
    ÙĪبÙĬ
    -0.07
    ayang
    -0.07
    оÑģÑĮ
    -0.07
    वà¤Ĥ
    -0.07
    аÑĤÑĥÑĢа
    -0.07
    cpy
    -0.07
    éħįç½®æĸ¹éĿ¢
    -0.07
    ราà¸ĩ
    -0.07
    पाल
    -0.07
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.10
    ä¸ŃçļĦ
    0.10
    -era
    0.09
    -style
    0.09
    ãģ«ãģĬãģijãĤĭ
    0.09
     equivalents
    0.08
     equivalent
    0.08
    ite
    0.08
    éĩĮçļĦ
    0.08
     counterparts
    0.08
    Activations Density 0.405%

    No Known Activations