© 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. 51013
    Prev
    Next
    INDEX
    Explanations

    cutting, slicing, intersecting geometric shapes

    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
     lagun
    -0.07
    ×ķ×¢
    -0.07
    /Error
    -0.07
    ointment
    -0.07
     ÑĥÑĤÑĢа
    -0.07
    åĴĮç»´æĬ¤
    -0.07
    èĢĮåĬªåĬĽ
    -0.07
    åŁ¹ä¼ĺ
    -0.07
    çļĦèĢĥçĶŁ
    -0.07
    tv
    -0.07
    POSITIVE LOGITS
    åĪĩåī²
    0.11
     slicing
    0.09
     intersects
    0.09
     coupe
    0.09
     cutting
    0.09
     intersect
    0.09
    åĪĩåī²æľº
    0.08
     slices
    0.08
     slic
    0.08
     cuts
    0.08
    Activations Density 0.004%

    No Known Activations