© 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. 12444
    Prev
    Next
    INDEX
    Explanations

    my own program

    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
    ox
    -0.08
    uzu
    -0.07
    iale
    -0.07
    åįģå¹´åīį
    -0.07
    oit
    -0.07
    escaping
    -0.07
    GED
    -0.07
    epe
    -0.07
    azu
    -0.07
     unexpectedly
    -0.07
    POSITIVE LOGITS
     similarly
    0.08
    åIJĮçIJĨ
    0.08
    类似
    0.07
    ç±»æݨ
    0.07
    imilar
    0.07
     similar
    0.07
    çĽ¸ä¼¼çļĦ
    0.07
    类似çļĦ
    0.07
    ä½łèĩªå·±çļĦ
    0.07
    å®ŀéĻħ
    0.07
    Activations Density 0.053%

    No Known Activations