© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37237
    Prev
    Next
    INDEX
    Explanations

    Natural Nigerian lyricist

    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
    å¤©åºľ
    -0.10
    æģĴ大
    -0.09
     recom
    -0.09
    æľ¬ç½ijç«Ļ
    -0.08
     eventName
    -0.08
    åĩĢ
    -0.08
    æļ´æ¶¨
    -0.08
    å¹ħ度
    -0.08
    TagName
    -0.08
    æµ
    -0.08
    POSITIVE LOGITS
    红æĹĹ
    0.10
    èĥ¡åIJĮ
    0.09
    UEL
    0.09
    iffe
    0.09
    uel
    0.09
    æ·¦
    0.09
    çĺ¾
    0.08
    еле
    0.08
    éĢĢå½¹åĨĽäºº
    0.08
    ä¾®
    0.08
    Activations Density 0.182%

    No Known Activations