© 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. 23793
    Prev
    Next
    INDEX
    Explanations

    multiple items or quantities

    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
    两次
    -0.14
    æIJ¬å®¶
    -0.10
    جب
    -0.09
    第äºĮ次
    -0.09
    offs
    -0.09
    æ¼ıæ´ŀ
    -0.09
    èĥ½åģļåĪ°
    -0.09
    äºĨä¸ĢäºĽ
    -0.09
     sept
    -0.09
     Kauf
    -0.09
    POSITIVE LOGITS
    ä¸Ģå¿ĥ
    0.10
    antic
    0.10
     далеко
    0.09
    åľ¨åIJĮä¸Ģ
    0.09
    åIJĮç±»
    0.09
    è½»æĿ¾
    0.09
    å¤ļåIJį
    0.08
    åĮ¡
    0.08
     simult
    0.08
    TimeStamp
    0.08
    Activations Density 0.254%

    No Known Activations