© 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. 31503
    Prev
    Next
    INDEX
    Explanations

    vhdx file, cell transplantation, .NET

    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
    ç¥ĸ
    -0.08
    天ä»Ļ
    -0.07
    adera
    -0.07
    enis
    -0.07
    Ĭ
    -0.07
    afil
    -0.07
     nô
    -0.07
     Palmas
    -0.07
    æĪ´
    -0.07
    æĶĺ
    -0.07
    POSITIVE LOGITS
    inous
    0.07
    .fp
    0.07
    Previous
    0.07
    £¼
    0.07
     ervoor
    0.07
    èµ°äºĨ
    0.07
    ç²¹
    0.07
    ä¹ĭåīįçļĦ
    0.06
     ere
    0.06
    £
    0.06
    Activations Density 0.568%

    No Known Activations