© 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. 22333
    Prev
    Next
    INDEX
    Explanations

    physics and engineering terms

    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
    éĩįçĶŁä¹ĭ
    -0.08
    ään
    -0.07
    veau
    -0.07
    åħ³æ³¨åħ¬ä¼Ĺåı·
    -0.07
    æĸ°æ½®
    -0.07
     Monta
    -0.07
    åĪ°æѤ
    -0.07
    óf
    -0.07
    è¡ĮéĹ´
    -0.07
    axe
    -0.07
    POSITIVE LOGITS
     _____
    0.07
     ____
    0.07
     __
    0.07
    åľ¨æŁIJ
    0.07
    裾
    0.07
    ä¸ĭåĪĹ
    0.06
    \"
    0.06
    大åѦæķĻæİĪ
    0.06
     incompet
    0.06
    \n
    0.06
    Activations Density 0.016%

    No Known Activations