© 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. 2014
    Prev
    Next
    INDEX
    Explanations

    numbered, named, labeled

    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
    %%%
    -0.07
    tecz
    -0.07
    andes
    -0.07
    åĨį说äºĨ
    -0.07
    ä¸Ģç²Ĵ
    -0.07
    æĬĬ人
    -0.07
    -looking
    -0.07
    jš
    -0.07
    uze
    -0.06
    天å°Ĭ
    -0.06
    POSITIVE LOGITS
     ulang
    0.11
    æ¸ħæ¥ļ
    0.08
    æĽ°
    0.08
    abeled
    0.08
    med
    0.08
    å¾Īæ¸ħæ¥ļ
    0.08
    ropping
    0.08
    ierung
    0.07
    à¸ķà¹Īาà¸ĩà¹Ĩ
    0.07
    umped
    0.07
    Activations Density 0.059%

    No Known Activations