© 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. 16792
    Prev
    Next
    INDEX
    Explanations

    using application

    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
    ä½łè¦ģæĺ¯
    -0.08
    agina
    -0.08
    æľīåIJį
    -0.07
    ilh
    -0.07
     famously
    -0.07
    Comple
    -0.07
    æł¹æį®ä¸įåIJĮçļĦ
    -0.07
    æľĢèijĹåIJįçļĦ
    -0.07
     famous
    -0.07
    æľīåIJįçļĦ
    -0.07
    POSITIVE LOGITS
    课é¢ĺç»Ħ
    0.07
    çłĶ究ä¸Ń
    0.07
    ä½łä»¬çļĦ
    0.07
    rome
    0.07
    ç¿Ķ
    0.07
    gat
    0.06
    课é¢ĺ
    0.06
    å¿ĹåĪļ
    0.06
    oud
    0.06
     vostro
    0.06
    Activations Density 0.272%

    No Known Activations