© 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. 24076
    Prev
    Next
    INDEX
    Explanations

    Middle East groups and figures

    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
    äºĨåĩł
    -0.09
    kip
    -0.09
    -angle
    -0.09
     alas
    -0.09
    è¿Ļæĸ¹éĿ¢
    -0.08
    blade
    -0.08
    çijĢ
    -0.08
    .*?)
    -0.08
    nger
    -0.08
    attle
    -0.08
    POSITIVE LOGITS
     mun
    0.10
    åľ¨æĪijåĽ½
    0.10
    amine
    0.10
    èŁĴ
    0.09
    ÑģмоÑĤÑĢ
    0.09
    å¾Ĺä½ı
    0.09
    å¨ĺå¨ĺ
    0.09
    naires
    0.09
    ä¸įå¿ħ
    0.08
    è¿ĻæĶ¯
    0.08
    Activations Density 0.003%

    No Known Activations