© 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. 10714
    Prev
    Next
    INDEX
    Explanations

    scientific, medical, or technical terms

    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
    /devices
    -0.09
    ibar
    -0.09
    ystems
    -0.09
    /cards
    -0.08
    ules
    -0.08
    /videos
    -0.08
    ÙĪعات
    -0.08
    ç´łçļĦ
    -0.08
    ÃŃso
    -0.07
    ellers
    -0.07
    POSITIVE LOGITS
    /original
    0.07
    лÑĭÒĽ
    0.07
    年为
    0.06
    车æīĭ
    0.06
    为æĸ°
    0.06
    ductory
    0.06
    éĻ¢æł¡çļĦ
    0.06
    车
    0.06
    æĢģ
    0.06
    orary
    0.06
    Activations Density 1.226%

    No Known Activations