© 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. 4042
    Prev
    Next
    INDEX
    Explanations

    SU(2) group notation contexts

    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
    æĽ´çĶŁ
    -0.08
           ↵↵
    -0.07
    č↵č↵č↵č↵
    -0.07
                ↵↵
    -0.06
    åĴĮ
    -0.06
    άÏģ
    -0.06
                    ↵↵
    -0.06
    èĮ´
    -0.06
    urig
    -0.06
    ç´¢æĢ§
    -0.06
    POSITIVE LOGITS
    ×ķ×¢
    0.08
    loch
    0.08
    iswa
    0.07
    awat
    0.07
    licas
    0.07
    uille
    0.07
    æģ©æĸ¯
    0.07
    æĸ¯åŁº
    0.07
    ä¸ļçļĦ
    0.06
    纳æĸ¯
    0.06
    Activations Density 0.009%

    No Known Activations