© 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. 33588
    Prev
    Next
    INDEX
    Explanations

    periods, numbers, and units of time

    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
    igte
    -0.08
    ich
    -0.08
    é¹ıé£ŀ
    -0.08
    iya
    -0.08
    иÑĩ
    -0.08
    enko
    -0.07
    ORY
    -0.07
    igts
    -0.07
    çĦī
    -0.07
    itch
    -0.07
    POSITIVE LOGITS
    å¡«
    0.09
     ______
    0.08
     ____
    0.08
     _____
    0.08
     ________
    0.08
    fill
    0.07
    ____
    0.07
    å¡«åĨĻ
    0.07
    填空
    0.07
     fills
    0.07
    Activations Density 0.029%

    No Known Activations