© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21565
    Prev
    Next
    INDEX
    Explanations

    sports doping and cheating scandals

    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
    åĿı
    -0.10
    çĻ¸
    -0.10
    æ³³
    -0.10
     дов
    -0.10
    èĢIJå¿ĥ
    -0.09
    ä¸įåħĭ
    -0.09
    ä¼´éļıçĿĢ
    -0.09
    /xhtml
    -0.09
    è¿Ŀæ³ķçĬ¯ç½ª
    -0.09
    çĽ¸ä¼´
    -0.09
    POSITIVE LOGITS
    bum
    0.12
    èħĭ
    0.09
    uth
    0.09
    éĽĩä½£
    0.09
    ä¸į符åIJĪ
    0.08
    åIJĮåŁİ
    0.08
    æĹĹ
    0.08
    èĢģå¦Ī
    0.08
    人èĦī
    0.08
    纹
    0.08
    Activations Density 0.022%

    No Known Activations