© 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. 63702
    Prev
    Next
    INDEX
    Explanations

    differential calculus 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
    erenc
    -0.08
    ä¸Ģæ´¾
    -0.08
    nist
    -0.07
    ARES
    -0.07
    wart
    -0.07
    èIJ½äºĨ
    -0.07
    ecker
    -0.07
    ourt
    -0.07
    ør
    -0.07
     Balik
    -0.07
    POSITIVE LOGITS
    å¾®å°ı
    0.10
     infinit
    0.08
     Interval
    0.08
    ä¸Ģå°ı
    0.08
    缸éĤ»
    0.08
     interval
    0.07
    éĩıçļĦ
    0.07
     tiny
    0.07
    interval
    0.07
    微微
    0.07
    Activations Density 0.003%

    No Known Activations