© 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. 25199
    Prev
    Next
    INDEX
    Explanations

    java/kotlin/c++/other code elements

    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
    éĩijå±±
    -0.07
    ¿
    -0.06
    è¿Ļæł·çļĦ
    -0.06
    aca
    -0.06
    èī¯
    -0.06
    ado
    -0.06
    æŶä¸ĭ
    -0.06
    Ãło
    -0.06
    Such
    -0.06
    xa
    -0.06
    POSITIVE LOGITS
    neb
    0.08
    zac
    0.08
    enta
    0.08
    euw
    0.08
    melden
    0.08
    astra
    0.07
    aeda
    0.07
    UEST
    0.07
    straints
    0.07
    icide
    0.07
    Activations Density 0.155%

    No Known Activations