© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48148
    Prev
    Next
    INDEX
    Explanations

    sudoku puzzles and solvers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪ©çī©
    -0.09
    ãĤīãģı
    -0.09
    VERTISE
    -0.08
    essim
    -0.08
    ellar
    -0.08
    (codec
    -0.08
    æĦıæĥ³ä¸įåĪ°
    -0.08
    otron
    -0.08
    ä¼ĺ
    -0.08
     sims
    -0.08
    POSITIVE LOGITS
     puzzle
    0.13
     Sudoku
    0.12
     sudoku
    0.11
     Puzzle
    0.11
    åĪģ
    0.11
    udoku
    0.10
    Solver
    0.10
     puzzles
    0.10
    è°ľ
    0.10
     solver
    0.10
    Activations Density 0.037%

    No Known Activations