© 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. 18117
    Prev
    Next
    INDEX
    Explanations

    catalysis and chain reactions

    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»ıè¿ĩå¤ļå¹´çļĦ
    -0.08
    é©»åįİ
    -0.07
    flat
    -0.07
    ابÙĤ
    -0.07
     gradu
    -0.07
    muz
    -0.07
    山人
    -0.07
    ANH
    -0.07
    irus
    -0.07
    ancia
    -0.07
    POSITIVE LOGITS
    循çݯ
    0.09
     cycle
    0.09
    ä¸įæģ¯
    0.09
     cycles
    0.09
    壮大
    0.08
    çĽ¸ä¼ł
    0.07
     berlangsung
    0.07
     sustaining
    0.07
     sust
    0.07
    è¿IJä½ľ
    0.07
    Activations Density 0.011%

    No Known Activations