© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51623
    Prev
    Next
    INDEX
    Explanations

    easily create, add, convert, find

    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
    泡沫
    -0.09
    泡
    -0.09
    å¾Ī大
    -0.09
    èĩĢ
    -0.09
    ä»İæĿ¥ä¸į
    -0.09
    ãĥĥãĥĹ
    -0.08
    nant
    -0.08
    éĺī
    -0.08
    åIJĥçļĦ
    -0.08
    าว
    -0.08
    POSITIVE LOGITS
    è¡¡éĩı
    0.09
    æ°Ķæ°Ľ
    0.09
    å¼Ģåĩº
    0.09
     ÙĪاÙĦس
    0.09
    ç©¿ä¸Ĭ
    0.09
     tan
    0.08
    mente
    0.08
    uss
    0.08
     dÃłng
    0.08
    planes
    0.08
    Activations Density 0.036%

    No Known Activations