© 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. 4512
    Prev
    Next
    INDEX
    Explanations

    years

    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
    arta
    -0.07
    BS
    -0.07
    indel
    -0.07
    _BS
    -0.07
    æĬĺ
    -0.07
    å·²èµŀè¿ĩ
    -0.07
    rata
    -0.06
    erne
    -0.06
    CLUDED
    -0.06
    rist
    -0.06
    POSITIVE LOGITS
    env
    0.07
    Úº
    0.07
    platform
    0.07
    海峡
    0.07
    quier
    0.07
    acing
    0.07
    æĸĩ件大å°ı
    0.06
    ׳×Ļת
    0.06
    umeric
    0.06
    让æĪij们ä¸Ģèµ·æĿ¥
    0.06
    Activations Density 0.001%

    No Known Activations