© 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. 30577
    Prev
    Next
    INDEX
    Explanations

    tennis tournament results

    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
    æĤĮ
    -0.09
    æīĵä»Ĺ
    -0.08
    éĽªå±±
    -0.08
    山水
    -0.08
     DUI
    -0.08
    rede
    -0.08
    åħļç»Ħç»ĩ
    -0.08
    -football
    -0.08
    паÑĤ
    -0.08
     dist
    -0.08
    POSITIVE LOGITS
     Tennis
    0.11
     Feder
    0.11
    ç½ijçIJĥ
    0.10
     полÑĥ
    0.10
     tennis
    0.10
     Wimbledon
    0.10
    åĽ½ç±į
    0.09
     mant
    0.09
    ç»Īç»ĵ
    0.09
    ç»ı纪
    0.09
    Activations Density 0.198%

    No Known Activations