© 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. 4367
    Prev
    Next
    INDEX
    Explanations

    competed in sports or 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
     xen
    -0.09
    æĿµ
    -0.09
     garden
    -0.09
    ants
    -0.09
    诸
    -0.08
    è±¢
    -0.08
    _VF
    -0.08
    lyn
    -0.08
    ugi
    -0.08
    ẩm
    -0.08
    POSITIVE LOGITS
    æ°´åŁŁ
    0.11
    æ°´ä¸Ĭ
    0.10
    çļĦä¹IJ趣
    0.10
    èį»
    0.10
     kayak
    0.10
    è´Ńç½®
    0.10
    èĬ¦
    0.10
    æ¼Ĥæµģ
    0.10
    æ·Ģ
    0.10
    æ°´æµģ
    0.10
    Activations Density 0.071%

    No Known Activations