© 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. 1499
    Prev
    Next
    INDEX
    Explanations

    sports competitions and championships

    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
    èµ·æĿ¥äºĨ
    -0.08
    habit
    -0.08
    ight
    -0.08
     loose
    -0.08
    ÑĤок
    -0.08
    isse
    -0.08
    åĽ´
    -0.08
     ÑĤож
    -0.08
    _bot
    -0.07
    ç¥Ń
    -0.07
    POSITIVE LOGITS
    该项
    0.10
    æ¼ķ
    0.09
    å±ĢéĻIJ
    0.09
    å¼ĢåĪĽ
    0.09
    æĥ³è±¡åĬĽ
    0.09
    交åıĭ
    0.09
    主åĬŀæĸ¹
    0.09
    otti
    0.09
    æĶ¹éĿ©åıijå±ķ
    0.09
    æĦıä¹ī
    0.08
    Activations Density 0.018%

    No Known Activations