© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8357
    Prev
    Next
    INDEX
    Explanations

    violation of rules

    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
    ä¸Ģ对
    -0.10
    ä¸Ģ份
    -0.10
     Carroll
    -0.10
     orchestr
    -0.09
    ä¸įä¼ļæľī
    -0.08
    еÐ
    -0.08
     calor
    -0.08
    gent
    -0.08
    getOption
    -0.08
    ä½Ĩä¹Ł
    -0.08
    POSITIVE LOGITS
    çݯèĬĤ
    0.11
    ä¸įåºĶ该
    0.10
    ä¾µçĬ¯
    0.10
    æĿ¥ä¸įåıĬ
    0.10
    ä¸į该
    0.10
    åºĶåıĬæŶ
    0.10
    é¾Ļæ¹ĸ
    0.10
    忽è§Ĩ
    0.10
    ÑĢож
    0.09
    以ä¸ĬçļĦ
    0.09
    Activations Density 0.041%

    No Known Activations