© 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. 63761
    Prev
    Next
    INDEX
    Explanations

    energy expenditure and 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
    åĵģç§įçļĦ
    -0.08
    ä¸įå¾Ĺ使çĶ¨
    -0.08
     maxLength
    -0.08
    éĻIJä½į
    -0.07
    磼
    -0.07
    opaque
    -0.07
    ä»·æł¼åIJĪçIJĨ
    -0.07
    ikkel
    -0.07
    -dialog
    -0.07
    åĵģ種
    -0.07
    POSITIVE LOGITS
    èĢĹèĥ½
    0.11
    èĢĹ
    0.10
     energy
    0.10
    çĥŃèĥ½
    0.09
     metabolism
    0.09
    èĥ½éĩı
    0.09
    çĥŃéĩı
    0.09
    energy
    0.09
    æĹºçĽĽ
    0.09
    èĬĤèĥ½
    0.09
    Activations Density 0.027%

    No Known Activations