© 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. 21064
    Prev
    Next
    INDEX
    Explanations

    liquid metal fast breeder reactors

    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
     gasto
    -0.08
    mes
    -0.07
    æĹłæ±¡æŁĵ
    -0.06
     landfill
    -0.06
    çħ§èĢĢ
    -0.06
    æĪIJç«ł
    -0.06
     gross
    -0.06
     expenditure
    -0.06
    lements
    -0.06
     workload
    -0.06
    POSITIVE LOGITS
    breaker
    0.08
    ä»»åħį
    0.07
    缸ä½į
    0.07
    phabet
    0.07
    产ä¸ļ转åŀĭåįĩ级
    0.07
    ä½į次
    0.07
     ladder
    0.07
    çīĮåı·
    0.07
    æĢ§åĪ¥
    0.07
     pen
    0.07
    Activations Density 0.495%

    No Known Activations