© 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. 65264
    Prev
    Next
    INDEX
    Explanations

    magnetic levitation and bearings

    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
    æīĽèµ·
    -0.08
    æĿ¡æĿ¡
    -0.07
    åĮħæīİ
    -0.07
     Wein
    -0.07
    åŃ£é£İ
    -0.07
    onal
    -0.07
    çĤ³
    -0.07
     Broken
    -0.07
     massacre
    -0.07
    çĶ·åĦ¿
    -0.07
    POSITIVE LOGITS
    æĤ¬æµ®
    0.09
     hovering
    0.09
     hover
    0.09
    .air
    0.09
    æĦŁåºĶ
    0.09
     hovered
    0.09
     magnetic
    0.08
     Hover
    0.08
    Hover
    0.08
     induction
    0.08
    Activations Density 0.077%

    No Known Activations