© 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. 48348
    Prev
    Next
    INDEX
    Explanations

    cultural influences and validity

    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
    éĢĢ
    -0.10
    åĵģ
    -0.08
    .ref
    -0.08
    æİĪæĿĥ
    -0.08
    ä¸įä¸Ĭ
    -0.08
    শ
    -0.08
    大éģĵ
    -0.08
    èijĹ
    -0.08
    éĨī
    -0.08
    shed
    -0.08
    POSITIVE LOGITS
    æĸĩåĮĸåĴĮ
    0.16
    æ°ijæĹıæĸĩåĮĸ
    0.16
     cultures
    0.15
     culturally
    0.15
    æĸĩåĮĸ
    0.14
    æĸĩåĮĸçļĦ
    0.14
    ä¹łä¿Ĺ
    0.14
    é£İä¿Ĺ
    0.14
     cultural
    0.13
     Cultural
    0.12
    Activations Density 0.152%

    No Known Activations