© 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. 63010
    Prev
    Next
    INDEX
    Explanations

    academic courses and subjects

    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
    ikon
    -0.10
    ÑĩÑĮ
    -0.09
    人å¿ĥ
    -0.09
    çıı
    -0.09
    æľīå¤ļ大
    -0.09
    ollen
    -0.08
    ìĦ¼íĦ°
    -0.08
    åĻª
    -0.08
    误
    -0.08
    /fw
    -0.08
    POSITIVE LOGITS
    ç§ij缮
    0.16
     courses
    0.15
    ä¸ĢéŨ
    0.14
    课ç¨ĭ
    0.12
     Courses
    0.11
     subjects
    0.11
     modules
    0.11
    å¼Ģ设
    0.10
    Courses
    0.10
    Modules
    0.10
    Activations Density 0.196%

    No Known Activations