© 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. 18106
    Prev
    Next
    INDEX
    Explanations

    website or site

    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
    第äºĮæī¹
    -0.09
    港
    -0.09
    atat
    -0.09
    ç»ĦåĽ¾
    -0.09
    æİĴéĻ¤
    -0.09
    ä¸Ģå¹ķ
    -0.09
    åĪĨæł¡
    -0.08
    ê³łìļĶ
    -0.08
    ãĤµãĤ¤
    -0.08
    家ä½ı
    -0.08
    POSITIVE LOGITS
    ç½ijç«Ļ
    0.20
     website
    0.17
    網ç«Ļ
    0.15
     ÑģайÑĤа
    0.14
     websites
    0.13
    å®ĺæĸ¹ç½ijç«Ļ
    0.13
    website
    0.12
     www
    0.12
     Website
    0.12
     site
    0.12
    Activations Density 0.196%

    No Known Activations