© 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. 32370
    Prev
    Next
    INDEX
    Explanations

    day and holidays

    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
    åįĬå¤ľ
    -0.09
    大æĸ¹
    -0.09
    ä¸Ģè¶Ł
    -0.09
    ovich
    -0.08
    åĿĬ
    -0.08
    ØŃÙĬÙĨ
    -0.08
    æ£ĺ
    -0.08
    æľīåĩłä¸ª
    -0.08
    ä¸Ģç«Ļ
    -0.08
    åħļå§Ķ
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸Ģ天
    0.15
     Day
    0.10
    _SID
    0.09
     day
    0.09
    æŃ£å¥½
    0.09
    Day
    0.09
    UNET
    0.09
    èĩ¼
    0.09
    çļĦæĹ¥åŃIJ
    0.09
    è¯ŀ
    0.09
    Activations Density 0.078%

    No Known Activations