© 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. 16584
    Prev
    Next
    INDEX
    Explanations

    knowledge of how things work

    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
     صÙģ
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    åij¢
    -0.08
    loff
    -0.08
    èĦļ
    -0.08
    å¾ĹåĪ°äºĨ
    -0.07
    èĩªåĬ¨åĮĸ
    -0.07
    绪
    -0.07
    à¸ŀา
    -0.07
     pursuits
    -0.07
    POSITIVE LOGITS
    æĢİä¹ĪåĽŀäºĭ
    0.10
    æ·±åĪ»çļĦ
    0.10
    è¡Įæĥħ
    0.10
    æľĢæĸ°çļĦ
    0.09
    éģij
    0.09
    çī¹çĤ¹
    0.09
    .background
    0.09
    æݨèįIJéĺħ读
    0.09
    æľĢæĸ°
    0.09
    èĥĮæĻ¯
    0.09
    Activations Density 0.135%

    No Known Activations