© 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. 14491
    Prev
    Next
    INDEX
    Explanations

    photon emission, light, display

    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
     голо
    -0.09
    голо
    -0.08
    é«ĺæłĩåĩĨ
    -0.08
    alanta
    -0.08
    ìŀ
    -0.08
    åħĭéļ¾
    -0.08
    æłĩåĩĨä¿¡æģ¯
    -0.08
    é«ĺæĬĢæľ¯
    -0.08
    μοÏħ
    -0.08
     alo
    -0.07
    POSITIVE LOGITS
     terrestrial
    0.11
     mundane
    0.10
    ä¸ĸä¿Ĺ
    0.10
    ä¿Ĺ
    0.10
    庸
    0.10
    èĦļè¸ıå®ŀåľ°
    0.10
    åĬ¡å®ŀ
    0.09
     terrestre
    0.09
    åĩ¡äºº
    0.09
    è¸ıå®ŀ
    0.09
    Activations Density 0.402%

    No Known Activations