© 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. 62756
    Prev
    Next
    INDEX
    Explanations

    one of these/those

    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
    夷
    -0.09
    累累
    -0.09
    antis
    -0.09
    ä»ĸä¼ļ
    -0.09
    leta
    -0.08
    UGHT
    -0.08
    ä¸Ģ个个
    -0.08
    ä¹ĥ
    -0.08
    ä¸ĭåįĬ
    -0.08
    åĨłåĨĽ
    -0.08
    POSITIVE LOGITS
    éĤ£ç§į
    0.14
    å¼ıçļĦ
    0.09
    æ²Ķ
    0.09
    è¿Ļç§į
    0.09
    æѤ类
    0.09
    uden
    0.09
    æѤç§į
    0.09
    éļıçĿĢ
    0.08
    ampoline
    0.08
    ãģĵãģĨãģĦãģĨ
    0.08
    Activations Density 0.052%

    No Known Activations