© 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. 1497
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with operations

    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
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    -0.08
    veal
    -0.08
    åĺĺ
    -0.08
    igon
    -0.08
    erbe
    -0.08
     '`
    -0.08
    çıĪ
    -0.08
    sdale
    -0.08
    IENTO
    -0.08
    PIO
    -0.08
    POSITIVE LOGITS
    oman
    0.06
    ims
    0.06
    —which
    0.06
    åºŀ
    0.06
    izard
    0.06
     Gim
    0.06
    èĢĮå¤į
    0.06
    Since
    0.06
    angu
    0.06
    óta
    0.06
    Activations Density 0.003%

    No Known Activations