© 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. 45579
    Prev
    Next
    INDEX
    Explanations

    Galois fields and extensions

    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
    มาà¸ĵ
    -0.07
    ixels
    -0.07
    fras
    -0.07
    Ñħло
    -0.07
    æ¼Ķ说
    -0.07
    -dot
    -0.07
    veu
    -0.07
    ted
    -0.07
    serie
    -0.07
    å¾ĹåĪ©
    -0.07
    POSITIVE LOGITS
    ois
    0.09
    ÑĹн
    0.07
    æĺł
    0.07
    ord
    0.07
    éĢĨ
    0.07
    åĢĴå½±
    0.06
     unordered
    0.06
    åĢĴ
    0.06
    å¯Ĩçłģ
    0.06
    urt
    0.06
    Activations Density 0.004%

    No Known Activations