© 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. 24303
    Prev
    Next
    INDEX
    Explanations

    Copyright year

    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
    åĩ¼
    -0.10
     Caul
    -0.09
    åľ¨æ¸¸æĪıä¸Ń
    -0.09
    _LINEAR
    -0.09
    åIJijå¤ĸ
    -0.08
    è¿Ļç§įæĸ¹å¼ı
    -0.08
    _authenticated
    -0.08
     Malta
    -0.08
    羣è¯ļ
    -0.08
     stro
    -0.08
    POSITIVE LOGITS
    åı«æĪij
    0.09
    èģļä¼ļ
    0.09
    hurst
    0.09
    项
    0.09
    çļĦçľ¼
    0.08
    aret
    0.08
    psilon
    0.08
    èĤ²åĦ¿
    0.08
    unched
    0.08
    voke
    0.08
    Activations Density 0.042%

    No Known Activations