© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9311
    Prev
    Next
    INDEX
    Explanations

    percentage of

    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
     Randolph
    -0.09
    é¢ĩ
    -0.09
    imore
    -0.09
    æ¸Ķ
    -0.09
     Wade
    -0.08
    à®´
    -0.08
    é«ĺ级
    -0.08
    åĪĽ
    -0.08
    è¿Ļç¯ĩ
    -0.08
    æľĢä½İ
    -0.08
    POSITIVE LOGITS
    ä¸įä¿¡
    0.10
    æĺ¯æĪij们
    0.10
    大éĥ¨åĪĨ
    0.10
    大å¤ļæķ°äºº
    0.10
    大éĥ¨åĪĨ人
    0.09
    ç»Ŀ大éĥ¨åĪĨ
    0.09
    0
    0.09
    大å¤ļæķ°
    0.09
    æĮĩæľĽ
    0.09
    5
    0.09
    Activations Density 0.184%

    No Known Activations