© 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. 62264
    Prev
    Next
    INDEX
    Explanations

    will/can/may followed by action

    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
    èĢģ人家
    -0.12
    人æ°ijæľįåĬ¡
    -0.12
    æīĢæľī人éĥ½
    -0.11
    ä¸İä¼Ĺä¸įåIJĮ
    -0.11
    大家ä¸Ģèµ·
    -0.11
    æĺ¯ä¸ª
    -0.11
    人çĶŁçļĦ
    -0.10
    太å°ij
    -0.10
    大家
    -0.10
    大家éĥ½
    -0.10
    POSITIVE LOGITS
     themselves
    0.15
     compos
    0.09
    éĿ¢ä¸´
    0.08
     Dylan
    0.08
    æ´¥
    0.08
    ä¹ĭéĹ´
    0.08
     Nag
    0.08
    acted
    0.08
    hip
    0.08
    ives
    0.08
    Activations Density 0.189%

    No Known Activations