© 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. 33439
    Prev
    Next
    INDEX
    Explanations

    vaccination and protection

    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
    é¹Ħ
    -0.10
    æ²»çIJĨ
    -0.10
    æݬ
    -0.09
    æķıæĦŁ
    -0.09
    æ¼Ĥæµģ
    -0.09
    quarter
    -0.09
     Perc
    -0.09
    寺
    -0.09
    ottom
    -0.09
    æ°´åĪ©å·¥ç¨ĭ
    -0.08
    POSITIVE LOGITS
    ä¿ĿæĬ¤
    0.11
    éĺ²æĬ¤
    0.10
    æĬĵ
    0.09
    åŀĭåı·
    0.09
    éĺ²å¾¡
    0.09
    ä¿Ŀå®ī
    0.09
     protection
    0.08
     commerc
    0.08
     ngừa
    0.08
    Protection
    0.08
    Activations Density 0.215%

    No Known Activations