© 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. 12721
    Prev
    Next
    INDEX
    Explanations

    accelerometer, acceleration, gyro, 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
    åIJĮæĢ§æģĭ
    -0.08
    _SSL
    -0.07
    énk
    -0.07
    ëĭ¥
    -0.07
    éĢĢ缩
    -0.07
    åĶ
    -0.07
    å¿ĥä¸Ĭ
    -0.07
    éclair
    -0.07
    æľŁåĨħ
    -0.07
    åħīæĺİçļĦ
    -0.07
    POSITIVE LOGITS
    éĻĢèŀº
    0.11
     gyro
    0.11
     accelerometer
    0.11
    é¢łç°¸
    0.10
     gy
    0.09
    éĩįåĬĽ
    0.09
    åĬłéĢŁåº¦
    0.09
     tilt
    0.09
     motion
    0.08
    åĢ¾æĸľ
    0.08
    Activations Density 0.071%

    No Known Activations