© 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. 35222
    Prev
    Next
    INDEX
    Explanations

    movie titles and software libraries

    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
    illo
    -0.10
    åĪ³
    -0.10
    IFY
    -0.09
    è§ı
    -0.09
    гоÑĢод
    -0.09
    æĮĩ纹
    -0.09
    ä¸¥æł¼èIJ½å®ŀ
    -0.09
     NOI
    -0.09
    aho
    -0.08
    ä¹IJæĦı
    -0.08
    POSITIVE LOGITS
    WithData
    0.10
    arella
    0.09
    ä¸Ĭå®ĺ
    0.09
    àºĩ
    0.08
    éĤĽ
    0.08
    Ùĩز
    0.08
    ÑijÑĢ
    0.08
    代
    0.08
     plat
    0.08
     Salvador
    0.08
    Activations Density 0.078%

    No Known Activations