© 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. 6642
    Prev
    Next
    INDEX
    Explanations

    ice hockey player season

    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
    åħ¬å¼Ģ
    -0.10
    æĶ¸
    -0.09
    çļĦæĪ¿åŃIJ
    -0.09
     Yup
    -0.09
    xee
    -0.09
    éī´
    -0.09
    æŶèĬĤ
    -0.09
    æĺİåªļ
    -0.08
    åľ°æĸ¹æĶ¿åºľ
    -0.08
    æĬ±æŃī
    -0.08
    POSITIVE LOGITS
    éĿ©
    0.10
    èĦī
    0.08
    æݨ
    0.08
    é«ĺåİĭ
    0.08
     Rol
    0.08
     badge
    0.08
    çķĻå®Ī
    0.08
    Pragma
    0.08
     convent
    0.08
    ancia
    0.08
    Activations Density 0.090%

    No Known Activations