© 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. 62060
    Prev
    Next
    INDEX
    Explanations

    "$p$–form gauge potentials"

    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
    ↵
    -0.08
    à¥ĩ
    -0.07
    s
    -0.06
    oot
    -0.06
    ت
    -0.06
    ع
    -0.06
    .,
    -0.06
    iates
    -0.05
    :
    -0.05
    ;)
    -0.05
    POSITIVE LOGITS
    ly
    0.12
    atre
    0.09
    elves
    0.09
    wards
    0.09
    à¸Ļà¹Į
    0.09
    unque
    0.09
    èĩªå·±
    0.09
    ikker
    0.08
    etheless
    0.08
    stairs
    0.08
    Activations Density 0.012%

    No Known Activations