© 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. 50845
    Prev
    Next
    INDEX
    Explanations

    month of year + announcement

    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¸»å¼ł
    -0.08
    çݰ身
    -0.08
     Mitt
    -0.08
    견
    -0.08
    Partition
    -0.08
    Instagram
    -0.08
    æ®ģ
    -0.08
    æĮij
    -0.07
    å¼ķ导
    -0.07
    ä¸ĢäºĮ
    -0.07
    POSITIVE LOGITS
    æ¶Īæģ¯ç§°
    0.12
    宣å¸ĥ
    0.11
    ä¼łæĿ¥
    0.11
     announcement
    0.11
    èİ·æĤī
    0.11
    æĸ°éĹ»åıijå¸ĥ
    0.10
     news
    0.10
     announc
    0.10
    åħ¬åijĬ
    0.10
     announcements
    0.10
    Activations Density 0.109%

    No Known Activations