© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36949
    Prev
    Next
    INDEX
    Explanations

    baseball positions

    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
    è¾¼ãĤģ
    -0.10
    è´¯
    -0.10
    liner
    -0.10
    æľ¬äºĭ
    -0.09
    heimer
    -0.09
    åĴĮå®ĮåĸĦ
    -0.09
    éĽī
    -0.09
    æ°´åĪ©å·¥ç¨ĭ
    -0.08
    ANCE
    -0.08
    ìłģìľ¼ë¡ľ
    -0.08
    POSITIVE LOGITS
    çĻ½éĵ¶
    0.10
    çĶ«
    0.09
    StartupScript
    0.09
    amu
    0.09
    ä¸ĬçļĦ
    0.08
    è¿Ļ个èģĮä¸ļ
    0.08
    æĭĽèģĺä¿¡æģ¯
    0.08
    .scalar
    0.08
    æĺİçŁ¥
    0.08
    åĬ©çIJĨ
    0.08
    Activations Density 0.004%

    No Known Activations