© 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. 20750
    Prev
    Next
    INDEX
    Explanations

    combinations, variations, diversity

    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
    ligh
    -0.07
    ber
    -0.07
    渡
    -0.07
    æĹłåıį
    -0.07
     Acad
    -0.07
     zuverläss
    -0.06
    æѤæŶçļĦ
    -0.06
    bers
    -0.06
    åĽłä¸ºæĺ¯
    -0.06
    lider
    -0.06
    POSITIVE LOGITS
     combinations
    0.13
    满足ä¸įåIJĮ
    0.11
    binations
    0.11
    éĢīæĭ©ä¸įåIJĮçļĦ
    0.11
     variations
    0.11
     permutations
    0.11
    å¤ļæł·æĢ§
    0.10
     diverse
    0.10
    å¤ļæł·åĮĸçļĦ
    0.10
    çļĦä¸įåIJĮ
    0.10
    Activations Density 0.081%

    No Known Activations