© 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. 51599
    Prev
    Next
    INDEX
    Explanations

    homeostasis and physiological processes

    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
    æīĢéĢī
    -0.08
    ç¬ĥ
    -0.08
     Yüks
    -0.08
    å¢ŀæĶ¶
    -0.07
    å¿ĥ仪
    -0.07
    Immutable
    -0.07
    å«Įçĸij
    -0.07
    elang
    -0.06
    åĪ»éª¨
    -0.06
    æĢĿæĥ³ä¸Ĭ
    -0.06
    POSITIVE LOGITS
    æŃ£å¸¸æĥħåĨµä¸ĭ
    0.16
    æŃ£å¸¸
    0.14
    çļĦæŃ£å¸¸
    0.14
    æŃ£å¸¸çļĦ
    0.14
    æŃ£å¸¸è¿IJè¡Į
    0.12
     normal
    0.12
     healthy
    0.11
     regulates
    0.11
     regulating
    0.11
    æŃ£å¸¸è¿IJ转
    0.11
    Activations Density 0.609%

    No Known Activations