© 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. 2114
    Prev
    Next
    INDEX
    Explanations

    names and locations

    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
    轶
    -0.10
    å´Ľ
    -0.09
    ä¸Ģ声
    -0.09
    ibal
    -0.09
    æĭ¼éŁ³
    -0.08
     Randall
    -0.08
    å¬ī
    -0.08
    iani
    -0.08
    讼
    -0.08
    è¿Ļåı¥è¯Ŀ
    -0.08
    POSITIVE LOGITS
    nick
    0.09
     ÐĴам
    0.09
     Melania
    0.09
    é»ijèī²
    0.09
    apo
    0.09
    ä½Ł
    0.09
    åľ¨å¸Ĥåľºä¸Ĭ
    0.08
    gart
    0.08
    å¤ĸå¥Ĺ
    0.08
    asters
    0.08
    Activations Density 0.110%

    No Known Activations