© 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. 57786
    Prev
    Next
    INDEX
    Explanations

    precipitation and weather events

    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
    ç§ĭ天
    -0.09
    ä¸ī个æľĪ
    -0.09
    两个æľĪ
    -0.09
    æĻ¾
    -0.09
    .mx
    -0.09
    ÑĦон
    -0.09
    æ°´åŁŁ
    -0.09
    åĽĽåŃ£
    -0.08
    Margin
    -0.08
    å¤ı天
    -0.08
    POSITIVE LOGITS
    vore
    0.10
    åľ¨å¤ĸ
    0.10
    _Dep
    0.10
    裾
    0.09
    æľ¬ç«Ļ
    0.09
    åľ¨äº¬
    0.09
    çľĭ好
    0.09
    ç«ĻçĤ¹
    0.09
    åĵģä½į
    0.09
    çĽijçĿ£æ£ĢæŁ¥
    0.09
    Activations Density 0.033%

    No Known Activations