© 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. 20879
    Prev
    Next
    INDEX
    Explanations

    harm, advice, lessons, wrong, cookies

    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
    hots
    -0.07
    çŁ
    -0.07
    arning
    -0.07
    eves
    -0.07
    æĬij
    -0.06
    mond
    -0.06
    >Show
    -0.06
    ÑīеÑĤ
    -0.06
    ulls
    -0.06
    ERING
    -0.06
    POSITIVE LOGITS
    à¸Ĺีà¹Īà¹Ģà¸ģิà¸Ķà¸Ĥึà¹īà¸Ļ
    0.14
     koju
    0.13
    人æīĢ
    0.12
    ä¸ŃæīĢ
    0.11
     коÑĤоÑĢÑĥÑİ
    0.11
     available
    0.11
    ä¸ĬæīĢ
    0.11
     jaki
    0.10
    æĪij们æīĢ
    0.10
     undertaken
    0.10
    Activations Density 0.995%

    No Known Activations