© 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. 18993
    Prev
    Next
    INDEX
    Explanations

    sports organizations or 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
    ven
    -0.08
    å¤ĸåįĸ
    -0.08
    abilities
    -0.08
    ail
    -0.08
    æªĶ
    -0.08
    åĬŁå¤«
    -0.08
    åĨĴ
    -0.08
    æłī
    -0.07
    queeze
    -0.07
     Kemp
    -0.07
    POSITIVE LOGITS
    åıįæĦŁ
    0.10
    é»İ
    0.10
     mái
    0.10
    çļĦ表æĥħ
    0.09
    çŀ½
    0.09
    æĪ´ä¸Ĭ
    0.09
    ÑĢÑĥж
    0.09
    ãĥįãĤ¿
    0.09
    ä»»ä½ķå½¢å¼ı
    0.09
    é»İæĺİ
    0.09
    Activations Density 0.004%

    No Known Activations