© 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. 55447
    Prev
    Next
    INDEX
    Explanations

    sports and locations

    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
    ç«
    -0.09
    è¿IJæ²³
    -0.09
    éĺŁåijĺ
    -0.09
    è¹ij
    -0.08
    è¿IJè´¹
    -0.08
    ÙĪÙĤ
    -0.08
     Duck
    -0.08
    车éĺŁ
    -0.08
    bane
    -0.08
    奸
    -0.08
    POSITIVE LOGITS
    æµģ转
    0.10
    ä¸ĢæĬ¹
    0.10
    ä¸Ģéģĵ
    0.10
    åħį责声æĺİ
    0.09
    éĢĨ
    0.09
    æĪIJé¾Ļ
    0.09
    è¾ĥ强çļĦ
    0.09
    è¶ĭåIJij
    0.09
    大éĿ¢ç§¯
    0.09
    pany
    0.09
    Activations Density 0.039%

    No Known Activations