© 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. 60617
    Prev
    Next
    INDEX
    Explanations

    division and district appellations

    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
    åľ¨ç½ijä¸Ĭ
    -0.10
    ä¸Ģå®ļçļĦ
    -0.09
    æŃ£åĢ¼
    -0.09
    grams
    -0.09
    Gram
    -0.09
    家åĸ»æĪ·æĻĵ
    -0.09
    è¾İ
    -0.09
    们çļĦ
    -0.08
    å±ĭ顶
    -0.08
    髯
    -0.08
    POSITIVE LOGITS
    寤
    0.11
    /right
    0.10
    .wp
    0.09
    ellt
    0.09
    enums
    0.08
    \Events
    0.08
    åIJĮåŁİ
    0.08
    íĻį
    0.08
    Ñĥнк
    0.08
    olan
    0.08
    Activations Density 0.073%

    No Known Activations