© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24056
    Prev
    Next
    INDEX
    Explanations

    special occasion or person

    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
    Negative Logits
    å°ıå¾®
    -0.09
     ech
    -0.09
    éĿ¢çĽ®
    -0.08
    azzi
    -0.08
    vy
    -0.08
    лаг
    -0.08
    大大
    -0.08
     каÑĩ
    -0.08
    ç§ij缮
    -0.08
    ech
    -0.08
    POSITIVE LOGITS
    æīĢåľ¨
    0.10
    Rare
    0.10
    ties
    0.10
    ä¹ĭå¤Ħ
    0.09
    ÑĨа
    0.09
    åľ°æ®µ
    0.09
    LEV
    0.09
    鹤
    0.09
    -looking
    0.08
    çļĦä¸Ģåijĺ
    0.08
    Activations Density 0.016%

    No Known Activations