© 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. 13228
    Prev
    Next
    INDEX
    Explanations

    non-equilibrium, entropy, systems

    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
     Nationwide
    -0.09
    kker
    -0.08
     scaleX
    -0.08
    ød
    -0.08
    åŃ¦ä¹łæĢģ度
    -0.08
    ษ
    -0.08
    æĶ¾äºĨ
    -0.08
    mig
    -0.07
    pit
    -0.07
    èĦ¸åŀĭ
    -0.07
    POSITIVE LOGITS
    ç
    0.10
     subsystem
    0.09
     systems
    0.08
    éĢłçī©
    0.08
    ç»´æĮģ
    0.08
     entropy
    0.08
     dissip
    0.07
    asa
    0.07
     maintaining
    0.07
    entropy
    0.07
    Activations Density 0.017%

    No Known Activations