© 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. 57955
    Prev
    Next
    INDEX
    Explanations

    sports 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
    icho
    -0.11
    æĪijä»¬åľ¨
    -0.11
    æĪijåľ¨
    -0.10
    æĪijåĴĮ
    -0.10
     Dev
    -0.10
    леÑĤ
    -0.10
    åĿį
    -0.09
    æĪij们éĥ½
    -0.09
    大家éĥ½
    -0.09
    ä½łæĥ³
    -0.09
    POSITIVE LOGITS
    aurus
    0.10
    éļ°
    0.09
    æĹ¥å¸¸
    0.08
    åŁĭ
    0.08
    åı¯çĶ¨
    0.08
    çļĦä¸Ģ
    0.08
    asu
    0.08
    /MIT
    0.08
    ä¹ı
    0.08
    .commons
    0.08
    Activations Density 0.012%

    No Known Activations