© 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. 44951
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    gence
    -0.09
    ingos
    -0.07
    inga
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    ible
    -0.07
    endom
    -0.07
    ej
    -0.07
    imony
    -0.07
    ingkatkan
    -0.06
    uzion
    -0.06
    POSITIVE LOGITS
    اء
    0.10
    اتÙĩÙħ
    0.09
    èĢĮä»Ĭ
    0.08
    ally
    0.08
    ìļ°
    0.08
    اراÙĨ
    0.08
    лла
    0.08
     бÑĥдÑĤо
    0.07
     constexpr
    0.07
    иÑİ
    0.07
    Activations Density 0.539%

    No Known Activations