© 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. 50972
    Prev
    Next
    INDEX
    Explanations

    symbols and mathematical operators

    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
    Ùĩ
    -0.12
    es
    -0.12
    çļĦ
    -0.12
    s
    -0.11
    ÛĮ
    -0.11
    äºĨ
    -0.10
    i
    -0.09
    ar
    -0.09
    ìĿĦ
    -0.09
    ed
    -0.09
    POSITIVE LOGITS
    jenigen
    0.11
    ments
    0.11
    اÙĭ
    0.10
    plevel
    0.10
    ë¦Ħ
    0.10
    centes
    0.10
    odore
    0.09
    tml
    0.09
    semb
    0.09
    imately
    0.09
    Activations Density 0.041%

    No Known Activations