© 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. 39198
    Prev
    Next
    INDEX
    Explanations

    derivative and dispersion

    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
    åĽĬ
    -0.08
    æıIJè¦ģ
    -0.07
    ozen
    -0.07
    å©Ĩ
    -0.07
    eria
    -0.07
    æīijéĿ¢
    -0.07
    æľ¬å®ŀçĶ¨æĸ°åŀĭ
    -0.07
    &action
    -0.06
    ontre
    -0.06
    æIJŃä¸Ĭ
    -0.06
    POSITIVE LOGITS
     steep
    0.08
    æĬ¤åį«
    0.08
    _userdata
    0.07
    hoven
    0.07
     tại
    0.07
    backs
    0.07
    matplotlib
    0.07
    atters
    0.07
    rait
    0.07
    æĶ¾å¤§éķľ
    0.07
    Activations Density 0.003%

    No Known Activations