© 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. 63025
    Prev
    Next
    INDEX
    Explanations

    already stated or asked

    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
    ogos
    -0.07
    arel
    -0.07
    sud
    -0.07
    elpers
    -0.07
    guard
    -0.07
    nitz
    -0.07
     ãĥĶ
    -0.06
    gena
    -0.06
    gan
    -0.06
    ubro
    -0.06
    POSITIVE LOGITS
     already
    0.21
    already
    0.19
    à¸Ńยูà¹Īà¹ģลà¹īว
    0.17
    Already
    0.17
    å·²ç»ıå¾Ī
    0.17
     Already
    0.16
     alred
    0.15
    å·²ç»ı
    0.15
    å·²ç»ıæľī
    0.15
     déjÃł
    0.15
    Activations Density 0.290%

    No Known Activations