© 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. 11939
    Prev
    Next
    INDEX
    Explanations

    structs and braces

    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
    ooth
    -0.07
    eppe
    -0.07
    å°ıé¢ĺ
    -0.06
    太ä¹ħ
    -0.06
    æľīåħ³äºİ
    -0.06
    èµĸ
    -0.06
    太快
    -0.06
    ëł
    -0.06
     glimpse
    -0.06
    erto
    -0.06
    POSITIVE LOGITS
    arkin
    0.07
     Tess
    0.07
    yna
    0.07
     erster
    0.07
    mira
    0.07
     competitiv
    0.07
    .bz
    0.07
     coinci
    0.07
    spinner
    0.06
    âĨĵâĨĵ
    0.06
    Activations Density 0.224%

    No Known Activations