© 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. 12132
    Prev
    Next
    INDEX
    Explanations

    machine learning code and papers

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æł¸å¿ĥåĮº
    -0.09
    åħ³çĪ±
    -0.09
    å®ĺæĸ¹å¾®ä¿¡
    -0.09
    è§Ĵ度æĿ¥çľĭ
    -0.08
     ÑĢол
    -0.08
    ä¿Ŀå®Ī
    -0.08
    è§Ĵ度çľĭ
    -0.08
    _pdu
    -0.08
    å®īåħ¨ä¿Ŀéļľ
    -0.08
    为广大
    -0.08
    POSITIVE LOGITS
    è®Ńç»ĥ
    0.09
     practition
    0.08
    èĴ¸
    0.08
    å¼ĢåıijèĢħ
    0.07
    -fashion
    0.07
    è¨ĵç·´
    0.07
    ocoder
    0.07
    .keras
    0.07
     обÑĥÑĩ
    0.07
    æ·ĺ
    0.07
    Activations Density 0.481%

    No Known Activations