© 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. 45846
    Prev
    Next
    INDEX
    Explanations

    CP violation and symmetry

    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
    òi
    -0.08
    ÙĤدر
    -0.07
    лÑıм
    -0.07
    erie
    -0.07
    лем
    -0.07
    eries
    -0.07
    õi
    -0.07
    ipas
    -0.07
    微信æī«çłģ
    -0.07
    èĦļæīĭ
    -0.07
    POSITIVE LOGITS
     symmetry
    0.08
    avis
    0.08
    imir
    0.07
    calar
    0.07
    inv
    0.07
     swap
    0.07
    oidal
    0.07
    tal
    0.07
    对称
    0.07
    rav
    0.06
    Activations Density 0.001%

    No Known Activations