© 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. 2046
    Prev
    Next
    INDEX
    Explanations

    reaction pathway mechanism

    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
    .sap
    -0.07
    è¿ĻäºĽä¸ľè¥¿
    -0.07
     |âĢ¢
    -0.07
    udes
    -0.07
    -0.07
    ÙĪØ®
    -0.07
    ils
    -0.07
     wd
    -0.06
    _accessor
    -0.06
    uti
    -0.06
    POSITIVE LOGITS
     meta
    0.08
    åħ¸
    0.08
    好äºĭ
    0.07
     favorita
    0.07
     spont
    0.07
     favorito
    0.07
    ä¸Ģåĩº
    0.07
    æĸ¹ç¨ĭå¼ı
    0.07
     sto
    0.07
    å¼ı为
    0.07
    Activations Density 0.016%

    No Known Activations