© 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. 2107
    Prev
    Next
    INDEX
    Explanations

    www. followed by domain parts

    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
    æĸĩåĮĸåĴĮ
    -0.10
    é¢ĺæĿIJ
    -0.09
    碴
    -0.08
    人æ°ijç½ij
    -0.08
    ä¸Ģå°ģä¿¡
    -0.08
    ëį°
    -0.08
    wins
    -0.08
    åªĴä½ĵæĬ¥éģĵ
    -0.08
    geom
    -0.08
    人们çļĦ
    -0.08
    POSITIVE LOGITS
    éĴ£
    0.09
    abouts
    0.08
    BuilderFactory
    0.08
     hã
    0.08
    VIRTUAL
    0.08
    æľįè£ħ
    0.08
    éĤ£æł·çļĦ
    0.08
    EFR
    0.08
    æĪIJç«ĭäºİ
    0.08
    ä¹ĭåĬĽ
    0.08
    Activations Density 0.055%

    No Known Activations