© 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. 34882
    Prev
    Next
    INDEX
    Explanations

    data availability and reporting

    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
    ç¼
    -0.09
    quisition
    -0.09
    è¯Ńæĸĩ
    -0.09
    åĪĽå§ĭ
    -0.09
    ongyang
    -0.09
     anthology
    -0.08
    æ¦ľé¦ĸ
    -0.08
     ба
    -0.08
    ä¸ĭè°ĥ
    -0.08
    ä¹Ŀé¾Ļ
    -0.08
    POSITIVE LOGITS
     journal
    0.10
    æĮ¡
    0.10
    åıij表
    0.09
     Excel
    0.09
    è¯ķéªĮ
    0.09
     اÙĦتÙĪاصÙĦ
    0.09
    è´Ł
    0.09
    å¸ĪåħĦ
    0.09
    stk
    0.08
    å§IJ
    0.08
    Activations Density 0.152%

    No Known Activations