© 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. 19457
    Prev
    Next
    INDEX
    Explanations

    energy metabolism

    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
    ¿IJ
    -0.08
    è¨Ģè¡Į
    -0.07
    幸éģĭ
    -0.07
     teles
    -0.07
     Grav
    -0.07
    æł¼æĸ¯
    -0.07
     Installer
    -0.07
    uur
    -0.07
    rimon
    -0.07
     coll
    -0.06
    POSITIVE LOGITS
     metabolism
    0.11
    ä¾Ľç»Ļ
    0.10
     metabolic
    0.10
    ä¾Ľ
    0.10
     supplying
    0.09
     supply
    0.09
     starving
    0.09
    Supply
    0.09
     supplies
    0.09
    supply
    0.09
    Activations Density 0.161%

    No Known Activations