© 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. 19143
    Prev
    Next
    INDEX
    Explanations

    robot arm, vision, light manipulation

    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
     withdrawals
    -0.07
    éĻįåİĭ
    -0.07
     withdrawal
    -0.06
     aromat
    -0.06
     Withdraw
    -0.06
    Withdraw
    -0.06
     motel
    -0.06
    å´©
    -0.06
    collapse
    -0.06
     drip
    -0.06
    POSITIVE LOGITS
     pose
    0.12
    Pose
    0.11
    çī©ä½ĵ
    0.11
    姿æĢģ
    0.11
     Kinect
    0.11
    çļĦ姿æĢģ
    0.10
     Pose
    0.10
    _pose
    0.10
    sensor
    0.10
    ä¼łæĦŁåĻ¨
    0.10
    Activations Density 0.471%

    No Known Activations