© 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. 16243
    Prev
    Next
    INDEX
    Explanations

    words following "are"

    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
    اء
    -0.09
    ânia
    -0.08
    imini
    -0.07
    Ù°
    -0.07
    uwen
    -0.07
    ण
    -0.07
    aneously
    -0.07
     nochmal
    -0.07
    zzi
    -0.07
    cione
    -0.07
    POSITIVE LOGITS
    æ³ķçŃī
    0.08
     ways
    0.08
     fewer
    0.08
    æĸ¹æ³ķæĿ¥
    0.08
    nt
    0.08
    /is
    0.07
    ways
    0.07
     ÑĤакже
    0.07
    nte
    0.07
    't
    0.07
    Activations Density 0.052%

    No Known Activations