© 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. 23653
    Prev
    Next
    INDEX
    Explanations

    supervision, supervisory, supervise, supervisors

    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
    ij¸
    -0.09
    ness
    -0.09
    佬
    -0.08
    NESS
    -0.08
    -bodied
    -0.08
    ¬
    -0.07
    -fashioned
    -0.07
     lá»ĩ
    -0.07
    å¦ŀ
    -0.07
    ington
    -0.07
    POSITIVE LOGITS
    /control
    0.09
    ä¸į严
    0.09
    ungan
    0.09
    iors
    0.08
     altında
    0.08
    ä¸įåĬĽ
    0.08
     ketat
    0.08
    elight
    0.08
    åĴĮé¼ĵåĬ±
    0.08
    ä¸įä½ı
    0.08
    Activations Density 0.020%

    No Known Activations