© 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. 33868
    Prev
    Next
    INDEX
    Explanations

    mirror symmetry, symmetry operations

    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
     teb
    -0.08
    ulette
    -0.08
    èµĥ
    -0.08
    æĹŃæĹ¥
    -0.07
    éļĭ
    -0.07
     Differential
    -0.07
    æĸ¬
    -0.07
    BuilderFactory
    -0.07
    ENTI
    -0.07
     differential
    -0.07
    POSITIVE LOGITS
    对称
    0.10
     symmetry
    0.10
     Sym
    0.09
    .sym
    0.09
    [::-
    0.09
    åıįåIJij
    0.09
     complementar
    0.08
    _sym
    0.08
    _inverse
    0.08
     sym
    0.08
    Activations Density 0.006%

    No Known Activations