© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 28276
    Prev
    Next
    INDEX
    Explanations

    science, books, and paleo

    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
    Ĺ
    -0.07
    åĩ«
    -0.07
    çĭ¬ç«ĭçļĦ
    -0.06
    对åѦçĶŁçļĦ
    -0.06
    è¾Ľåĭ¤çļĦ
    -0.06
    ãĥ«ãĥĪ
    -0.06
    ipe
    -0.06
     independently
    -0.06
    åĬłæĭ¿å¤§
    -0.06
    å¾·æĸ¯
    -0.06
    POSITIVE LOGITS
     اÙĦدÙĨÙĬا
    0.07
    íĮ¬
    0.07
    een
    0.07
    sä
    0.07
    iecz
    0.07
    Topology
    0.07
    inheiten
    0.07
    üsse
    0.07
    cina
    0.07
    CP
    0.06
    Activations Density 0.001%

    No Known Activations