© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-CHAT-65K
    7. 45613
    Prev
    Next
    INDEX
    Explanations

    rivers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ожеÑĤ
    -0.24
     doGet
    -0.21
     circulated
    -0.19
    åij¼åĴĮ
    -0.19
    æĶ¹éĿ©åıijå±ķ
    -0.19
    UnitTest
    -0.19
    æµ·æ°´
    -0.18
    #
    -0.18
    arto
    -0.18
     opr
    -0.18
    POSITIVE LOGITS
    River
    0.28
    æ²³
    0.28
     river
    0.26
     upstream
    0.24
    两岸
    0.24
     downstream
    0.23
    banks
    0.23
    æ²³éģĵ
    0.23
     sông
    0.22
    readcr
    0.22
    Activations Density 0.110%

    No Known Activations