© 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. 2607
    Prev
    Next
    INDEX
    Explanations

    football teams

    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
    沩
    -0.10
    顺
    -0.09
    çIJĨäºĭéķ¿
    -0.09
    ä¼ģä¸ļæĸĩåĮĸ
    -0.09
    vale
    -0.09
    åİ¿åŁİ
    -0.08
    anas
    -0.08
    å±Ģéķ¿
    -0.08
     guit
    -0.08
    èĽ®
    -0.08
    POSITIVE LOGITS
    æľīèī²
    0.10
    åªĴ
    0.10
    çĶ¸
    0.09
    /perl
    0.09
    褪
    0.09
    æİ¥è¿ĩ
    0.08
    .navigateTo
    0.08
    åĨħéĻĨ
    0.08
    æĢĽ
    0.08
    åĩłåIJį
    0.08
    Activations Density 0.018%

    No Known Activations