© 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. 49876
    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
    :\/\/
    -0.09
    带
    -0.08
    _CONVERT
    -0.08
    æį²
    -0.08
    èµģ
    -0.08
    emun
    -0.07
    áĥĿáĥij
    -0.07
    airs
    -0.07
    å¹´æľŁ
    -0.07
    auen
    -0.07
    POSITIVE LOGITS
     symmetry
    0.13
    对称
    0.12
     Sym
    0.11
    sym
    0.10
     simpl
    0.10
    ç®ĢåĮĸ
    0.10
    Sym
    0.09
     symmetric
    0.09
     simplific
    0.08
     simplify
    0.08
    Activations Density 0.002%

    No Known Activations