© 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. 12314
    Prev
    Next
    INDEX
    Explanations

    symmetry breaking

    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
    coop
    -0.08
    .gz
    -0.07
    icus
    -0.07
     matrimoniale
    -0.07
    zze
    -0.07
    ontre
    -0.07
    ä¿ĿæķĻ
    -0.07
    stal
    -0.07
    croft
    -0.07
    voc
    -0.07
    POSITIVE LOGITS
     symmetry
    0.10
     underlying
    0.07
    对称
    0.07
    åĬłæĮģ
    0.07
    -inspired
    0.07
    ymm
    0.07
     Sym
    0.07
    贯穿
    0.07
    -breaking
    0.07
     sym
    0.07
    Activations Density 0.009%

    No Known Activations