© 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. 56727
    Prev
    Next
    INDEX
    Explanations

    lived or continue to live

    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
    ury
    -0.09
    KE
    -0.08
    èĥ½å¤Łè®©
    -0.08
    rets
    -0.08
    anko
    -0.08
     Ling
    -0.08
    WORDS
    -0.08
    éªĩ
    -0.08
    æĺ¯éĿŀ
    -0.08
    ä¼ı
    -0.08
    POSITIVE LOGITS
    ä¸ĢçĽ´åľ¨
    0.11
    没è§ģè¿ĩ
    0.10
    çļĦ责任
    0.10
    使çĶ¨æĿĥ
    0.09
    çľģæķĻèĤ²
    0.09
    ä¸Ģè´¯
    0.09
    çļĦ第ä¸Ģ个
    0.09
    ä»İæĿ¥æ²¡
    0.09
    ingle
    0.09
    ç¼Ŀ
    0.09
    Activations Density 0.054%

    No Known Activations