© 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. 54636
    Prev
    Next
    INDEX
    Explanations

    sports leagues and championships

    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
    éĥ¨éķ¿
    -0.09
    çĭŃ
    -0.09
    åIJĦè¡ĮåIJĦ
    -0.08
     Orch
    -0.08
    æ¸Į
    -0.08
    è¸
    -0.08
    ä¸Ģè·¯ä¸Ĭ
    -0.08
    å¼ıçļĦ
    -0.08
    æķĻè®Ń
    -0.08
    POSITIVE LOGITS
    åı²ä¸Ĭ
    0.10
    éħļ
    0.09
    éĶ¦æłĩèµĽ
    0.09
    æ·Į
    0.09
    æĺ¶
    0.09
    ä¹ĭ乡
    0.09
    çĸĥ
    0.09
    LETE
    0.09
    çķĮ第ä¸Ģ
    0.08
     Nation
    0.08
    Activations Density 0.080%

    No Known Activations