© 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. 31904
    Prev
    Next
    INDEX
    Explanations

    optimization problems and graph theory

    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
    érique
    -0.08
    é»ı
    -0.08
    ussen
    -0.08
    建ç«ĭèµ·
    -0.08
    æŀ¶
    -0.07
    è°¥
    -0.07
    æĢ»äº§åĢ¼
    -0.07
    æĸij
    -0.07
     advant
    -0.07
    驾
    -0.07
    POSITIVE LOGITS
    éĺĻ
    0.10
     SCIP
    0.10
    æ±Ĥå©ļ
    0.10
    æŀ¢çº½
    0.10
    æĶ»åĿļ
    0.09
    éĺı
    0.09
    çªģçł´åı£
    0.09
    梳
    0.09
    solver
    0.09
    æŁĵ
    0.09
    Activations Density 0.189%

    No Known Activations