© 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. 7911
    Prev
    Next
    INDEX
    Explanations

    oscillating or oscillations

    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
    isman
    -0.10
    çal
    -0.10
    eness
    -0.09
    wards
    -0.09
    edly
    -0.08
    ctor
    -0.08
    èݱåĿŀ
    -0.08
     dioxide
    -0.08
    resher
    -0.08
    duto
    -0.08
    POSITIVE LOGITS
    èĩªå¦Ĥ
    0.10
    åĬ¨çļĦ
    0.09
    ation
    0.09
    ingly
    0.08
    ulating
    0.08
    ulation
    0.08
    ierende
    0.08
    лиÑĢÑĥ
    0.08
    atory
    0.08
    åĻ¨çļĦ
    0.08
    Activations Density 0.013%

    No Known Activations