© 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. 27364
    Prev
    Next
    INDEX
    Explanations

    yield and harvest quantity

    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
    asca
    -0.10
    å¾Ĺ罪
    -0.10
    æĺ¯çĶ¨æĿ¥
    -0.09
     Liqu
    -0.09
    ç»ĦåIJĪ
    -0.09
    åĭĩ
    -0.09
    å°ıåºĹ
    -0.08
    æĹ¶æ®µ
    -0.08
    è¿¢
    -0.08
    åIJ¸çº³
    -0.08
    POSITIVE LOGITS
    产éĩı
    0.22
    æĶ¶èİ·
    0.20
    丰æĶ¶
    0.19
    æĶ¶çĽĬ
    0.16
     yield
    0.16
     harvest
    0.15
     yields
    0.15
    产åĩº
    0.14
    yield
    0.12
    åĩºåĵģ
    0.12
    Activations Density 0.082%

    No Known Activations