© 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. 47026
    Prev
    Next
    INDEX
    Explanations

    with cement, steel, gas, concrete, gel

    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
    æĺ¯ä¸ĢåĪĩ
    -0.07
    æ½ľåľ¨çļĦ
    -0.07
    æīĢæľīçļĦ
    -0.07
    лкÑĥ
    -0.07
    imits
    -0.06
    åĽ½åħ¬
    -0.06
    ë¥Ń
    -0.06
    就让
    -0.06
     potenz
    -0.06
    å·ŀçļĦ
    -0.06
    POSITIVE LOGITS
     either
    0.08
    æĿ¥èĩª
    0.08
    appropri
    0.08
    æĿ¥èĩªä¸ŃåĽ½
    0.07
    ä¸įæ¼ı
    0.07
     gunfire
    0.07
    ä¾Ĩèĩª
    0.07
    人次
    0.07
    IfNeeded
    0.07
    å°Ĩèĩ³
    0.07
    Activations Density 0.367%

    No Known Activations