© 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. 56962
    Prev
    Next
    INDEX
    Explanations

    for providing information or examples

    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
    Ùģرد
    -0.09
    dings
    -0.09
    mant
    -0.09
    æīĢåľ¨çļĦ
    -0.09
    åīįéĿ¢
    -0.09
    iding
    -0.08
    å©
    -0.08
    âĿı
    -0.08
    inst
    -0.08
     tact
    -0.08
    POSITIVE LOGITS
    æĽ´å¤ļä¿¡æģ¯
    0.11
    äºĨè§£æĽ´å¤ļ
    0.10
     further
    0.10
    è¿Ľä¸ĢæŃ¥
    0.09
    éĢ²ä¸ĢæŃ¥
    0.09
    echa
    0.09
    èķ¤
    0.09
    æĽ´å¤ļ
    0.08
    æĭ³
    0.08
    æĬĺ
    0.08
    Activations Density 0.075%

    No Known Activations