© 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. 38808
    Prev
    Next
    INDEX
    Explanations

    learning tools and apps

    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
    ĥģ
    -0.11
     barrels
    -0.10
    æ°ijæĦı
    -0.10
    èĤ¼
    -0.09
    æĨĭ
    -0.09
    ç»ķ
    -0.09
    巨人
    -0.09
     اÙĦØŃÙĬ
    -0.09
    é¦ĭ
    -0.09
     coun
    -0.08
    POSITIVE LOGITS
    å¤įä¹ł
    0.14
    å·©åĽº
    0.12
    è®°å¿Ĩ
    0.11
    åѦåĪ°
    0.11
    åį¡çīĩ
    0.10
    ä¸įå¿ĺ
    0.09
    éģĹå¿ĺ
    0.09
    éķ¿æķĪæľºåĪ¶
    0.09
    éªĬ
    0.09
    æİĮæı¡äºĨ
    0.09
    Activations Density 0.075%

    No Known Activations