© 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. 56418
    Prev
    Next
    INDEX
    Explanations

    physical interactions and senses

    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
    æł¼å¼ıçļĦ
    -0.08
    å²ģ以ä¸ĬçļĦ
    -0.07
    égor
    -0.07
    YPD
    -0.07
    FormatException
    -0.07
     traumatis
    -0.07
    eck
    -0.07
    æł¼å¼ı
    -0.07
     niên
    -0.07
    æĥ¶
    -0.07
    POSITIVE LOGITS
     mediated
    0.08
     interactions
    0.07
     nuclear
    0.07
     ÑıдеÑĢ
    0.07
    æ¡Į
    0.07
    uclear
    0.07
     particle
    0.07
     binding
    0.07
     atomic
    0.07
     reun
    0.07
    Activations Density 0.004%

    No Known Activations