© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2372
    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
    witter
    -0.09
    å«©
    -0.07
    å°½
    -0.07
    Ú¯ÛĮر
    -0.07
    corner
    -0.07
     corners
    -0.07
    iru
    -0.07
    coce
    -0.07
    dead
    -0.06
    ç¦ıçĶ°
    -0.06
    POSITIVE LOGITS
    ë¥
    0.09
     creating
    0.08
    缴å¾Ħ
    0.08
    æĹĭ转
    0.08
     rotating
    0.08
     create
    0.08
    à¸ģารสรà¹īาà¸ĩ
    0.08
     Creates
    0.07
     diameter
    0.07
     spins
    0.07
    Activations Density 0.005%

    No Known Activations