© 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. 31087
    Prev
    Next
    INDEX
    Explanations

    news sections and roles

    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
    庵
    -0.10
    LEC
    -0.09
     Documentation
    -0.09
    æĹħé¦Ĩ
    -0.09
    å¼ĵ
    -0.09
    èĪī
    -0.09
    é£İåIJ¹
    -0.09
    åĬ¡
    -0.09
    诱
    -0.08
    è¿ĩåĪĨ
    -0.08
    POSITIVE LOGITS
    æĬ¥éģĵ
    0.13
    ä¸ĢåĪĻ
    0.12
    æĹ¥æĬ¥éģĵ
    0.10
    è´¢ç»ı
    0.10
    åij¨åĪĬ
    0.10
    åł±å°İ
    0.10
    æłı缮
    0.09
    dent
    0.09
    èĬĤ缮ä¸Ń
    0.09
    dispatch
    0.09
    Activations Density 0.346%

    No Known Activations