© 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. 60905
    Prev
    Next
    INDEX
    Explanations

    asking questions or reporting issues

    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
    .undefined
    -0.07
    éĢļãĤĬ
    -0.07
    oup
    -0.07
    æľīæĦŁ
    -0.07
    semi
    -0.07
    主æķĻç»ĥ
    -0.07
    æĪIJç«ĭæĹ¥æľŁ
    -0.07
    æ´Ľä¼Ĭ
    -0.07
    Publication
    -0.07
    æľī礼
    -0.07
    POSITIVE LOGITS
    èĸª
    0.08
    NotFoundError
    0.08
    æĿIJ
    0.07
    ellas
    0.07
    wd
    0.07
    å¹ħ
    0.07
    ienz
    0.07
    Tar
    0.06
     Tar
    0.06
    ulum
    0.06
    Activations Density 0.002%

    No Known Activations