© 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. 47344
    Prev
    Next
    INDEX
    Explanations

    numbers and periods

    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
     Absol
    -0.07
    enko
    -0.06
     Ex
    -0.06
    ster
    -0.06
    handler
    -0.06
    andia
    -0.06
    umah
    -0.06
    urre
    -0.06
    zis
    -0.06
    аÑĪ
    -0.06
    POSITIVE LOGITS
    iance
    0.08
    è²Į
    0.08
    okok
    0.07
    ibel
    0.07
    icom
    0.07
    kép
    0.07
    主æĮģåı¬å¼Ģ
    0.07
    венÑĮ
    0.07
    thouse
    0.07
     Newtown
    0.07
    Activations Density 0.024%

    No Known Activations