© 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. 49167
    Prev
    Next
    INDEX
    Explanations

    kinetics of rate

    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
    ç£ħ
    -0.07
    çŁŃæľŁ
    -0.07
     conserv
    -0.07
    omentum
    -0.07
    atitude
    -0.07
     scarc
    -0.07
    apped
    -0.07
     Bakal
    -0.07
    odem
    -0.06
    ç«Ļ
    -0.06
    POSITIVE LOGITS
     kinetics
    0.09
    çļĦè¿Ļä¸Ģ
    0.08
    éĢŁçİĩ
    0.08
     Blow
    0.08
    å¾Īæħ¢
    0.08
    /process
    0.07
     mechan
    0.07
    æĩ¦
    0.07
     speeding
    0.07
    é¢ĦçĥŃ
    0.07
    Activations Density 0.027%

    No Known Activations