© 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. 43455
    Prev
    Next
    INDEX
    Explanations

    free services

    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
    ãģŁãĤĵ
    -0.08
    �t
    -0.07
    éħ
    -0.07
    边走
    -0.07
     tremend
    -0.07
    paralleled
    -0.07
    antz
    -0.07
    createForm
    -0.07
    à¸ģร
    -0.07
    :start
    -0.07
    POSITIVE LOGITS
    aster
    0.07
    iz
    0.07
    æĦıè§ģåĴĮ建议
    0.07
    uze
    0.07
    æĺ¯éĿŀ常
    0.07
    æĪij们æĺ¯
    0.06
    stellungen
    0.06
     Lage
    0.06
    ood
    0.06
    à¥Īया
    0.06
    Activations Density 0.509%

    No Known Activations