© 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. 28559
    Prev
    Next
    INDEX
    Explanations

    rotation and motion

    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
     Span
    -0.09
    淹没
    -0.08
    åijĬ
    -0.08
    娥
    -0.07
    妾
    -0.07
     airspace
    -0.07
    Inject
    -0.07
     Lancaster
    -0.07
    Span
    -0.07
    çĮ®
    -0.07
    POSITIVE LOGITS
    åºķéĥ¨çļĦ
    0.08
     iç
    0.07
    è¿IJåĬ¨ä¸Ń
    0.07
     geri
    0.07
    åºķéĥ¨
    0.07
     bottom
    0.07
     torque
    0.07
     internal
    0.07
    è¿IJåĬ¨çļĦ
    0.06
    odu
    0.06
    Activations Density 0.010%

    No Known Activations