© 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. 30355
    Prev
    Next
    INDEX
    Explanations

    examples, numbering, and files

    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
    illian
    -0.07
    èIJ½å®ŀ好
    -0.07
    gar
    -0.06
    orc
    -0.06
    cs
    -0.06
    ụn
    -0.06
    å
    -0.06
    aster
    -0.06
    fa
    -0.06
    or
    -0.06
    POSITIVE LOGITS
    cac
    0.08
    енÑģи
    0.07
    igel
    0.07
    apon
    0.07
    åŁİå¸Ĥä¸Ń
    0.07
    ubr
    0.07
    CustomAttributes
    0.07
    }:{
    0.07
    arrer
    0.07
    apons
    0.07
    Activations Density 0.149%

    No Known Activations