© 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. 57365
    Prev
    Next
    INDEX
    Explanations

    Boston sports teams

    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
    pped
    -0.10
    ç¼®
    -0.09
    åĩĨç¡®æĢ§
    -0.09
    æĪijåĴĮ
    -0.09
    ä¼łæĴŃ
    -0.08
    ç§ijæĬĢ大åѦ
    -0.08
    aped
    -0.08
    ags
    -0.08
    æīĢåľ¨åľ°
    -0.08
     Ag
    -0.08
    POSITIVE LOGITS
    ses
    0.10
    è¯Ŀ说
    0.09
    rena
    0.08
    Ø®ÙĬ
    0.08
    ilenames
    0.08
    åĻ«
    0.08
    çĥĺ
    0.08
    æħİ
    0.08
    åŃ¦å®¶
    0.08
    楯
    0.08
    Activations Density 0.013%

    No Known Activations