© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39710
    Prev
    Next
    INDEX
    Explanations

    former name or title

    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
    大大å°ı
    -0.09
    ä¸ĩåıĺ
    -0.08
    ogenesis
    -0.08
    akit
    -0.08
    usif
    -0.08
    spre
    -0.07
    uari
    -0.07
    atik
    -0.07
    AsStream
    -0.07
    ä½¿ä½ł
    -0.07
    POSITIVE LOGITS
    çļĦä¸Ģç§į
    0.10
    çĶ¨æĿ¥
    0.10
    ä¹ĭä¸Ģ
    0.09
     shorthand
    0.09
    çļĦä¸Ģéĥ¨åĪĨ
    0.08
    çļĦä¸Ģ種
    0.08
    ä¸ŃæĮĩ
    0.08
    ä¸ŃçļĦä¸Ģç§į
    0.08
    çļĦä¸Ģç§įæĸ¹å¼ı
    0.07
    çĶ¨ä¾Ĩ
    0.07
    Activations Density 0.179%

    No Known Activations