© 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. 19277
    Prev
    Next
    INDEX
    Explanations

    numbers before common nouns

    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
    ä¹Łæĺ¯ä¸Ģç§į
    -0.10
    ç¿ħ
    -0.10
    鬣
    -0.10
     болÑĮÑĪое
    -0.09
    å¾Ĺ天
    -0.09
    éĶ£
    -0.09
    ç¯Ļ
    -0.09
    çĶŁäº§åĴĮ
    -0.08
    ä¹Łæĺ¯éĿŀ常
    -0.08
    åıĮçľ¼
    -0.08
    POSITIVE LOGITS
    æľīçļĦ
    0.10
    åįķ纯çļĦ
    0.10
    对çĿĢ
    0.10
    /licenses
    0.09
     lẫn
    0.09
    aos
    0.09
    Äķ
    0.09
    ä¸ĵ
    0.09
    _capability
    0.09
    icon
    0.08
    Activations Density 0.115%

    No Known Activations