© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38346
    Prev
    Next
    INDEX
    Explanations

    in what way

    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
    ä¸įæĺ¯ä¸Ģ个
    -0.10
    è£½ä½ľ
    -0.09
     Laden
    -0.09
    æĸ¯åŁº
    -0.09
    èĩ
    -0.08
    ÑģÑĤавлен
    -0.08
    åľ¨ä¸Ģ个
    -0.08
    оÑĩка
    -0.08
    /pre
    -0.08
    è¯ļ
    -0.08
    POSITIVE LOGITS
     ways
    0.16
    æĦıæĥ³ä¸įåĪ°
    0.14
     Ways
    0.12
    ãģĦãģĭ
    0.11
    æĸ¹å¼ı
    0.09
    æ®ĭ
    0.09
    éªļ
    0.09
    ways
    0.09
     ÑģпоÑģоб
    0.09
    rimp
    0.09
    Activations Density 0.065%

    No Known Activations