© 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. 61595
    Prev
    Next
    INDEX
    Explanations

    child health and youth issues

    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
    æľīçļĦ人
    -0.11
    éĢĭ
    -0.09
    atron
    -0.09
    ابت
    -0.09
    vell
    -0.09
    ä¸ĭåij¨
    -0.09
    æķ¬ä¸ļ
    -0.08
    è´Łè´£ä»»
    -0.08
    èģĮå·¥
    -0.08
    _Frame
    -0.08
    POSITIVE LOGITS
    -nil
    0.09
    _VO
    0.09
    agon
    0.08
    æł¹åŁº
    0.08
    ikel
    0.08
    å²Ĺ
    0.08
    åĿĹ
    0.08
    活泼
    0.08
    оÑģÑĮ
    0.08
    .functional
    0.08
    Activations Density 0.077%

    No Known Activations