© 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. 60252
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and mathematical 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
    ech
    -0.07
    åIJĮæł·æĺ¯
    -0.06
    ipt
    -0.06
    æľī天
    -0.06
    i
    -0.06
    ä¸įèĥľ
    -0.06
    otic
    -0.06
    uling
    -0.06
    鸦
    -0.06
    tt
    -0.06
    POSITIVE LOGITS
    OUGH
    0.08
    adiens
    0.08
    odable
    0.08
    hci
    0.07
    çļĦè¿Ļä¸Ģ
    0.07
    -Identifier
    0.07
    rani
    0.07
    ÙĪاÙħ
    0.07
     dégrad
    0.07
    encv
    0.07
    Activations Density 0.002%

    No Known Activations