© 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. 4325
    Prev
    Next
    INDEX
    Explanations

    sports media and broadcasts

    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
    欢è¿İæĤ¨
    -0.09
    æį¢äºĨ
    -0.09
    è¾ĺ
    -0.09
    交æį¢
    -0.09
    ç»ŃèĪª
    -0.09
    æľīçļĦ人
    -0.09
    è§ĩ
    -0.09
    ä¸į代表
    -0.09
    ivate
    -0.08
    ç²Ł
    -0.08
    POSITIVE LOGITS
    æĽ´æľī
    0.10
    åŁĭ
    0.09
    à¸īà¸ļ
    0.09
    å®īæİĴ
    0.08
    å¿ĥæĥħ
    0.08
    atori
    0.08
    è¿Ļåĩłä¸ª
    0.08
    oga
    0.08
    ä¹Łä¸įæķ¢
    0.08
    å¾¹
    0.08
    Activations Density 0.005%

    No Known Activations