© 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. 5342
    Prev
    Next
    INDEX
    Explanations

    major world cities

    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
    ì§Ŀ
    -0.09
    该æĿij
    -0.08
    èµ°åħ¥
    -0.08
    enti
    -0.08
    oon
    -0.08
     Shawn
    -0.08
    orro
    -0.08
    eus
    -0.08
    岫
    -0.08
    å·¥ä½ľäººåijĺ
    -0.08
    POSITIVE LOGITS
    éĥ½å¸Ĥ
    0.10
    马æĭīæĿ¾
    0.09
    %D
    0.09
    åľ¨åħ¨åĽ½
    0.09
    åIJĦåĮº
    0.09
    æĪ¿ä»·
    0.08
    ä¸Ģ侧
    0.08
    个æĢ§
    0.08
    çī¹åĪ«æĺ¯
    0.08
    ulan
    0.08
    Activations Density 0.114%

    No Known Activations