© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19598
    Prev
    Next
    INDEX
    Explanations

    topological properties and definitions

    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
    æīĵåĩº
    -0.08
    æѤäºĭ
    -0.08
    èĽĻ
    -0.08
    æľīæĽ´å¥½çļĦ
    -0.08
    baugh
    -0.08
    麽
    -0.08
    åģĥ
    -0.08
    åľ¨åIJĮä¸Ģ
    -0.08
    姿
    -0.08
    åĪ³
    -0.08
    POSITIVE LOGITS
    éĽĨåIJĪ
    0.09
    <Point
    0.09
    æĦıè¯ĨåĪ°
    0.08
    åºıåĪĹ
    0.08
    æļ§æĺ§
    0.08
    åģĩæĹ¥
    0.08
    ç°
    0.08
    _Point
    0.08
    è¿ĿèĥĮ
    0.08
    å°ıå§IJå§IJ
    0.08
    Activations Density 0.348%

    No Known Activations