© 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. 8915
    Prev
    Next
    INDEX
    Explanations

    promises us, He heard and answered

    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
    WC
    -0.09
    åľ°éĿ¢
    -0.09
    ä¸Ĭå¸Ŀ
    -0.08
     pr
    -0.08
     Amer
    -0.07
    æĮij
    -0.07
    ULAR
    -0.07
    br
    -0.07
     ground
    -0.07
    åIJĦ
    -0.07
    POSITIVE LOGITS
    abet
    0.10
    ç¥Ĥ
    0.09
    æľ¬æĿ¥å°±
    0.09
    à¹ģà¸Ĺ
    0.09
    èĤĩ
    0.09
    æݧèĤ¡éĽĨåĽ¢
    0.09
    apiro
    0.09
     hung
    0.09
    ä¾Ľç»Ļ
    0.09
    妳
    0.09
    Activations Density 0.045%

    No Known Activations