© 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. 48668
    Prev
    Next
    INDEX
    Explanations

    mathematical groups and algebra

    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
    è¯ħ
    -0.08
    åĦ¿çļĦ
    -0.07
    è¿ĻåIJį
    -0.07
    stående
    -0.06
    谨记
    -0.06
    اÛĮÙĦ
    -0.06
    tida
    -0.06
    jumbotron
    -0.06
    æ·Ĩ
    -0.06
    agé
    -0.06
    POSITIVE LOGITS
    ically
    0.09
    oxel
    0.08
    ropy
    0.08
    ÚĨÙĩ
    0.08
    ic
    0.08
    oidal
    0.08
    稼
    0.08
    UnderTest
    0.08
    bras
    0.07
    -of
    0.07
    Activations Density 0.018%

    No Known Activations