© 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. 60797
    Prev
    Next
    INDEX
    Explanations

    how to improve

    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
    arris
    -0.10
    ä¸ĢèĪ¬çļĦ
    -0.09
    สมา
    -0.08
    SUP
    -0.08
    PAD
    -0.08
     typo
    -0.08
    еÑĢÑĮ
    -0.08
    åħµåĻ¨
    -0.08
    choose
    -0.07
    åĿĬ
    -0.07
    POSITIVE LOGITS
    æľĢä½³
    0.12
     ways
    0.12
    çļĦæľĢä½³
    0.12
    æĽ´å¥½åľ°
    0.11
    å°½åı¯èĥ½
    0.11
    娣
    0.11
    继ç»Ńä¿ĿæĮģ
    0.11
    èĥ½è®©
    0.10
     best
    0.10
    å®ŀæĸ½æĸ¹æ¡Ī
    0.10
    Activations Density 0.080%

    No Known Activations