© 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. 61779
    Prev
    Next
    INDEX
    Explanations

    nanocrystals and nanostructures

    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
    è¡®
    -0.09
    妥
    -0.09
    åĸĢ
    -0.08
    ading
    -0.08
    ç§ijåѦçłĶ究
    -0.08
    æŃ£å®Ĺ
    -0.08
    鬣
    -0.08
    弦
    -0.08
    èij©
    -0.08
    éĤª
    -0.08
    POSITIVE LOGITS
    chen
    0.10
    çķĻä½ı
    0.10
    ãģªãģĦãģĵãģ¨
    0.09
    ç»ĵæŀĦ
    0.09
    ÑĩаÑĤ
    0.09
    ä¸Ĭä¸ĭ游
    0.09
    å¢ĥçķĮ
    0.08
    structures
    0.08
    ONO
    0.08
    ãģ§ãģįãģ¦
    0.08
    Activations Density 0.650%

    No Known Activations