© 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. 55294
    Prev
    Next
    INDEX
    Explanations

    plot or sketch a graph

    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
    çĶ¨å¾Ĺ
    -0.08
    æ¶ĪèĢĹ
    -0.07
    extract
    -0.07
     legacy
    -0.07
    orr
    -0.07
     Extract
    -0.07
    æıIJåıĸ
    -0.07
    çIJ³çIJħ
    -0.07
    edia
    -0.06
    åĩĿç¥ŀ
    -0.06
    POSITIVE LOGITS
     plotted
    0.11
    plot
    0.11
    æııç»ĺ
    0.10
     sketch
    0.10
     plot
    0.10
    æıı
    0.10
    ç»ĺåĪ¶
    0.10
     plotting
    0.10
     Sketch
    0.10
     graph
    0.10
    Activations Density 0.011%

    No Known Activations