© 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. 33570
    Prev
    Next
    INDEX
    Explanations

    time for or to

    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
    omes
    -0.09
    èĶ½
    -0.09
    odyn
    -0.09
    WithIdentifier
    -0.09
    æŶæŶ
    -0.09
    é¢ĨæĤŁ
    -0.09
    éģ®
    -0.09
     BÃŃ
    -0.09
    çĸı
    -0.09
    çĮª
    -0.08
    POSITIVE LOGITS
    è¯Ŀ说
    0.08
    èįı
    0.08
    æĹłéĻIJ
    0.08
    ä¼Ĭæĭī
    0.08
    itur
    0.08
    鬼
    0.07
    çłĶ究æĬ¥åijĬ
    0.07
    æī«ä¸Ģæī«
    0.07
    åļ¼
    0.07
    /load
    0.07
    Activations Density 0.018%

    No Known Activations