© 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. 11979
    Prev
    Next
    INDEX
    Explanations

    light intensity and radiation units

    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
    eking
    -0.07
    é²ľæĺİçļĦ
    -0.07
    bersome
    -0.07
    unti
    -0.07
    ewn
    -0.07
     lengths
    -0.07
    æ¹ĸéĩĮ
    -0.07
     Tela
    -0.07
    åŃĺåĤ¨ç©ºéĹ´
    -0.07
    æ·±çļĦ
    -0.07
    POSITIVE LOGITS
     intensity
    0.11
    æºIJ
    0.10
     delivered
    0.10
    æºIJçļĦ
    0.10
    Intensity
    0.09
     transmitted
    0.09
    ources
    0.09
     irradi
    0.09
    çħ§å°Ħ
    0.09
     flux
    0.09
    Activations Density 0.017%

    No Known Activations