© 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. 56238
    Prev
    Next
    INDEX
    Explanations

    calyx, corolla, phyll

    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
    å³Ļ
    -0.08
    è¾ķ
    -0.08
    ç»Īäºİ
    -0.08
    /LICENSE
    -0.08
     pac
    -0.08
    çħĮ
    -0.08
    orous
    -0.08
     thermal
    -0.08
     thread
    -0.07
    ajo
    -0.07
    POSITIVE LOGITS
    辨
    0.10
    严å¯Ĩ
    0.10
    æľĿ
    0.09
    è¿ľæĸ¹
    0.09
    åįķ身
    0.09
    éĴ¿
    0.09
    éĵĥ
    0.09
    æĹłå½¢
    0.09
    èįī
    0.09
    æ¯ıèĤ¡
    0.09
    Activations Density 0.084%

    No Known Activations