© 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. 36065
    Prev
    Next
    INDEX
    Explanations

    president or vice president

    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
    çŀ°
    -0.10
    iane
    -0.09
    å¼ºåĽ½
    -0.09
    riel
    -0.08
     lean
    -0.08
    æ¶İ
    -0.08
    æ©Ľ
    -0.08
    peria
    -0.08
    纪æ£ĢçĽijå¯Ł
    -0.08
     Orth
    -0.08
    POSITIVE LOGITS
    мед
    0.10
    veral
    0.09
    æĪ·å¤ĸ
    0.09
    uggy
    0.09
    åľ¨æ¸¸æĪıä¸Ń
    0.09
    chandle
    0.09
    åģĮ
    0.09
    ä¸įåłª
    0.08
    糯
    0.08
    縻
    0.08
    Activations Density 0.012%

    No Known Activations