© 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. 53594
    Prev
    Next
    INDEX
    Explanations

    annual growth statistics

    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
    æľĪæľ«
    -0.10
    æĿ¥èĩª
    -0.08
    BlockSize
    -0.08
     Copp
    -0.08
    izons
    -0.08
    å¤ļå¹´
    -0.08
    еÑģÑĤи
    -0.08
    ä¼ļåľ¨
    -0.08
    ä¼ļ对
    -0.08
     ÑģпоÑģоб
    -0.08
    POSITIVE LOGITS
    ä¸ĬåįĬå¹´
    0.10
    æµIJ
    0.09
    æ¸IJ
    0.09
    çļĦå·¥ä½ľ
    0.09
     alone
    0.09
    èİĨ
    0.08
    çľĭçĹħ
    0.08
    çĤİçĥŃ
    0.08
     Weston
    0.08
    çļĦ表çİ°
    0.08
    Activations Density 0.058%

    No Known Activations