© 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. 22494
    Prev
    Next
    INDEX
    Explanations

    Borneo, Sumatra

    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
     Pháp
    -0.09
    诸侯
    -0.09
    ingly
    -0.09
    诵
    -0.09
    é«ĺè´µ
    -0.09
    à¸ģระà¸Ĺ
    -0.08
    åł¤
    -0.08
    è¿Ļç§įæĸ¹å¼ı
    -0.08
    å·©
    -0.08
    å¾Ĭ
    -0.08
    POSITIVE LOGITS
    鼶è·Ŀ离
    0.11
    ç¡Ŀ
    0.10
    ewis
    0.09
    merc
    0.09
    樽
    0.09
    çīĪæĿĥ
    0.09
    èķī
    0.09
    ãĥ¤
    0.09
    转载请
    0.09
    æĺ§
    0.08
    Activations Density 0.027%

    No Known Activations