© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52095
    Prev
    Next
    INDEX
    Explanations

    steady state equilibrium balance

    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
    Negative Logits
    æľ¬èī²
    -0.07
     seguida
    -0.07
    缴æİ¥ä»İ
    -0.07
    itek
    -0.07
    óm
    -0.07
    Loading
    -0.07
    大å¼Ģ
    -0.07
    ÏĦÏī
    -0.07
    丰å¯Į
    -0.07
    åĪ«ç¦»
    -0.07
    POSITIVE LOGITS
    平衡
    0.13
     balance
    0.12
     equilibrium
    0.12
     stable
    0.11
     steady
    0.11
     balances
    0.11
    ilibrium
    0.11
    steady
    0.10
    balance
    0.10
     balanced
    0.10
    Activations Density 0.011%

    No Known Activations