© 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. 6067
    Prev
    Next
    INDEX
    Explanations

    website domains and publications

    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
    管çIJĨç³»ç»Ł
    -0.10
    held
    -0.09
    æģ¤
    -0.09
     Sol
    -0.09
    èŀºæĹĭ
    -0.08
    æĴ·
    -0.08
     routine
    -0.08
    åľ¨æ·±åľ³
    -0.08
    æĢĢæĬ±
    -0.08
    æııåĨĻ
    -0.07
    POSITIVE LOGITS
    æĸ°éĹ»ç½ij
    0.13
    åij¨åĪĬ
    0.13
    ç½ij
    0.13
    æĹ¥æĬ¥
    0.13
    æĻļæĬ¥
    0.12
    æĿĤå¿Ĺ
    0.11
    .com
    0.11
    .net
    0.10
    .cn
    0.10
    æ³Ħ
    0.10
    Activations Density 0.276%

    No Known Activations