© 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. 9333
    Prev
    Next
    INDEX
    Explanations

    floor plans and meetings

    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
    elaar
    -0.09
    å¹´æĺ¥èĬĤ
    -0.08
    zelfde
    -0.08
    à§ĥ
    -0.08
    订éĺħä¸ĵæłı
    -0.08
    ãĥ¬ãĥ¼ãĤ·ãĥ§ãĥ³
    -0.08
    ãģ¨ãģĵãĤįãģ§ãģĻ
    -0.08
    aph
    -0.08
    eland
    -0.08
    Úº
    -0.08
    POSITIVE LOGITS
    ings
    0.08
    warts
    0.07
    ัà¸ģ
    0.07
    ideos
    0.07
    amento
    0.07
    izzi
    0.06
    oldem
    0.06
    ingly
    0.06
    locked
    0.06
    boards
    0.06
    Activations Density 0.010%

    No Known Activations