© 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. 8000
    Prev
    Next
    INDEX
    Explanations

    first or second item

    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
    ie
    -0.07
    æĺł
    -0.07
    l
    -0.07
    èĢĮåĩº
    -0.07
    ir
    -0.07
    åIJķ
    -0.06
    i
    -0.06
    è¦ģçŁ¥éģĵ
    -0.06
    ig
    -0.06
    lu
    -0.06
    POSITIVE LOGITS
    ItemList
    0.07
    å¹²èĦĨ
    0.07
    istan
    0.07
    ellas
    0.07
    ÙĪÙĬÙĨ
    0.07
    eku
    0.07
    KET
    0.07
    BoundingClientRect
    0.07
    gev
    0.07
    리ìĬ¤
    0.07
    Activations Density 0.001%

    No Known Activations