© 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. 43606
    Prev
    Next
    INDEX
    Explanations

    referred to or known as

    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
    дÑĢеÑģ
    -0.08
    .dup
    -0.08
    çļĦæĪIJåĪĨ
    -0.08
    åİŁåĪ¤
    -0.08
     következ
    -0.08
    æĩ¿
    -0.07
    lada
    -0.07
    toj
    -0.07
    æľĢæĸ°æĽ´æĸ°
    -0.07
    åīįåįģ
    -0.07
    POSITIVE LOGITS
    称为
    0.15
    ç®Ģ称
    0.14
    称ä¹ĭ为
    0.13
    称è°ĵ
    0.13
     name
    0.13
    ç§°ä½ľ
    0.13
     called
    0.13
    åIJį为
    0.13
    åı«åģļ
    0.13
    称
    0.12
    Activations Density 0.883%

    No Known Activations