© 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. 34131
    Prev
    Next
    INDEX
    Explanations

    German articles and subsequent words

    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
    ized
    -0.08
    mente
    -0.08
    izarre
    -0.08
    ücks
    -0.08
    âĸ·
    -0.07
    ModelProperty
    -0.07
    ÙħÙĥÙĨ
    -0.07
    izing
    -0.07
    trak
    -0.06
    lease
    -0.06
    POSITIVE LOGITS
     meisten
    0.15
    Ø©
    0.11
    zelfde
    0.09
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    0.08
     οÏĢοία
    0.08
    ore
    0.08
     beiden
    0.08
     cuales
    0.08
    itto
    0.08
    äºĨæĪij
    0.08
    Activations Density 0.009%

    No Known Activations