© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36375
    Prev
    Next
    INDEX
    Explanations

    categories of topics

    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
    Sdk
    -0.10
    ocio
    -0.09
     dụ
    -0.09
    çĵ¢
    -0.09
    æĦıåij³
    -0.09
    æį¢æĿ¥
    -0.09
    é²Ľ
    -0.09
    çī
    -0.09
    âŀ¥
    -0.08
    tek
    -0.08
    POSITIVE LOGITS
    åı²ä¸Ĭ
    0.10
    ä¸įå¾Ĺä¸į说
    0.10
    åIJĮè¡Į
    0.10
    åĨįä¹Łæ²¡æľī
    0.10
    çİ°çĬ¶
    0.10
    åľ¨æĪij
    0.09
    çķĮ
    0.09
    çļĦåľ°ä½į
    0.09
    ä½ĵ系建设
    0.09
    çķĮçļĦ
    0.09
    Activations Density 0.165%

    No Known Activations