© 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. 27518
    Prev
    Next
    INDEX
    Explanations

    estar verb auxiliary

    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
    ¹
    -0.09
    érica
    -0.09
    inds
    -0.09
    ä¸ĢåĪ»
    -0.08
    az
    -0.08
    atty
    -0.08
    Ģ
    -0.08
    ots
    -0.08
    azen
    -0.08
    river
    -0.08
    POSITIVE LOGITS
    çļĦ
    0.10
    ÑģÑı
    0.08
    nt
    0.08
    nya
    0.08
    åĴĮ
    0.07
    를
    0.07
    -vous
    0.06
    Dettagli
    0.06
    -
    0.06
    ablish
    0.06
    Activations Density 0.034%

    No Known Activations