© 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. 59433
    Prev
    Next
    INDEX
    Explanations

    US cities and states

    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
    举é£İ
    -0.09
    è½µ
    -0.08
    rack
    -0.08
     ÑģобÑģÑĤвенно
    -0.08
    åľ¨å½ĵåľ°
    -0.08
    åŀĦ
    -0.08
    åľ¨åľ°ä¸Ĭ
    -0.08
    åĮºåĨħ
    -0.08
    пол
    -0.08
    ungan
    -0.08
    POSITIVE LOGITS
    å¥
    0.09
    åĮ¡
    0.09
    éĨĴ
    0.09
    ozo
    0.08
    æľĢ容æĺĵ
    0.08
    grim
    0.08
    awai
    0.08
    æł·åŃIJ
    0.08
    åĢĻ
    0.08
    aly
    0.08
    Activations Density 0.106%

    No Known Activations