© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15893
    Prev
    Next
    INDEX
    Explanations

    scientific contexts

    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
    ä¸Ī
    -0.08
    ivi
    -0.07
    大åĨĽ
    -0.06
    è¿ĻæĹłçĸij
    -0.06
     Ukra
    -0.06
    itz
    -0.06
    ä¹IJäºİ
    -0.06
    tera
    -0.06
    tsky
    -0.06
    kons
    -0.06
    POSITIVE LOGITS
    æıļ
    0.08
    atron
    0.07
    iot
    0.07
    жом
    0.07
    stown
    0.07
    .Reader
    0.07
    ÏģÏĩ
    0.07
    orate
    0.07
    ¾
    0.07
    æīį好
    0.07
    Activations Density 0.003%

    No Known Activations