© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23218
    Prev
    Next
    INDEX
    Explanations

    line spectra, emission lines

    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
    ä»Ģä¹Īæł·çļĦ人
    -0.08
     акÑĤивов
    -0.07
    kina
    -0.07
    è¿ĩ度çļĦ
    -0.07
    åIJģ
    -0.07
     SWAT
    -0.07
    èįŁ
    -0.07
    udou
    -0.07
    æĬĬåŃ¦ä¹ł
    -0.07
    è¿Ļæł·çļĦ人
    -0.07
    POSITIVE LOGITS
     emitted
    0.10
     emission
    0.10
     emisión
    0.10
    ä¸ĢæĿ¡æĿ¡
    0.09
    åıijå°Ħ
    0.09
     emissions
    0.08
    ocket
    0.08
    _emit
    0.08
     series
    0.08
     famous
    0.08
    Activations Density 0.003%

    No Known Activations