© 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. 38242
    Prev
    Next
    INDEX
    Explanations

    postoperative recovery

    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
    deaux
    -0.08
    ecker
    -0.08
    .lu
    -0.07
    epy
    -0.07
    æĬķ
    -0.07
    奢ä¾Ī
    -0.07
    moni
    -0.07
    æıIJé«ĺèѦæĥķ
    -0.07
    ÙĪÙĨس
    -0.07
    रà¥įफ
    -0.07
    POSITIVE LOGITS
     afterward
    0.12
     afterwards
    0.10
     hasilnya
    0.08
    -after
    0.08
     resulting
    0.07
    ׼×Ķ
    0.07
    éĥ¨åĪĨç»ĦæĪIJ
    0.07
     after
    0.07
    ä¸Ģä½ĵåĮĸ
    0.07
    RESULT
    0.07
    Activations Density 0.338%

    No Known Activations