© 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. 60696
    Prev
    Next
    INDEX
    Explanations

    URLs ending in .ly or .gl

    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
    çŁ¥éģĵèĩªå·±
    -0.10
    lessness
    -0.09
    åıŃ
    -0.09
    uner
    -0.09
     Crosby
    -0.09
    ultiply
    -0.09
     Daly
    -0.08
    ograd
    -0.08
    çī¹åĪ«æĺ¯
    -0.08
    stype
    -0.08
    POSITIVE LOGITS
    errick
    0.09
    æĭ¿åĩºæĿ¥
    0.09
    éĽĢ
    0.09
    亿ä¸ĩ
    0.08
    åĪĥ
    0.08
    æĶ¾å¼Ģ
    0.08
    æĸ¹éĴĪ
    0.08
    s
    0.08
    墨
    0.08
    æĸ¹æīį
    0.08
    Activations Density 0.003%

    No Known Activations