© 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. 55914
    Prev
    Next
    INDEX
    Explanations

    sports competitions and professional activities

    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
    æī«ä¸Ģæī«
    -0.10
    æĺ¾
    -0.09
    åįģå¹´åīį
    -0.09
    åĮĸåѦåĵģ
    -0.09
    èµ·åĪ°
    -0.08
    ADVERTISEMENT
    -0.08
    å§Ķå±Ī
    -0.08
    oden
    -0.08
     Nob
    -0.08
    odon
    -0.08
    POSITIVE LOGITS
    ç«ŀæĬĢ
    0.13
    èµĽäºĭ
    0.12
    æ¯ĶèµĽ
    0.11
    è§ĴéĢIJ
    0.11
    è¿IJåĬ¨åijĺ
    0.10
     пÑĢоÑĦеÑģÑģиона
    0.10
    ç«ŀäºī
    0.10
     professional
    0.10
    æ¯Ķè³½
    0.10
    ç«ŀèµĽ
    0.10
    Activations Density 0.326%

    No Known Activations