© 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. 48039
    Prev
    Next
    INDEX
    Explanations

    irrigation and watering

    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
    uden
    -0.09
    é£İåij³
    -0.09
    æŃ£æĸĩ
    -0.09
    罡
    -0.09
    宿
    -0.08
    侦
    -0.08
    åī¥ç¦»
    -0.08
    tight
    -0.08
    åľ¨æĹ¥æľ¬
    -0.08
    Cow
    -0.08
    POSITIVE LOGITS
    æµĩæ°´
    0.17
    æµĩ
    0.14
    çģĮæºī
    0.13
     watering
    0.10
    æ¾
    0.10
    补水
    0.10
    é¢ijçİĩ
    0.10
    æ¯ıåij¨
    0.09
    æºī
    0.09
    uplic
    0.09
    Activations Density 0.019%

    No Known Activations