© 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. 25758
    Prev
    Next
    INDEX
    Explanations

    units of measure for physical quantities

    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
    xies
    -0.09
    ož
    -0.08
    ero
    -0.08
    اضÙĬ
    -0.08
    Edited
    -0.08
    èĩ³å°ijæľī
    -0.08
    ekom
    -0.08
    yani
    -0.08
    ergeb
    -0.08
    -Core
    -0.08
    POSITIVE LOGITS
     dönÃ¼ÅŁ
    0.08
    èĢį
    0.07
    æį¢ç®Ĺ
    0.07
    .translate
    0.06
    害
    0.06
     K
    0.06
     pad
    0.06
     transl
    0.06
     translate
    0.06
     translation
    0.06
    Activations Density 0.009%

    No Known Activations