© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2006
    Prev
    Next
    INDEX
    Explanations

    eccentric Mr

    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
    íĴĪ
    -0.11
    æѤ类
    -0.09
    沸
    -0.09
    rong
    -0.09
     tá»ĩ
    -0.08
    aurus
    -0.08
    irth
    -0.08
     вÑģÑı
    -0.08
    naire
    -0.08
    GES
    -0.08
    POSITIVE LOGITS
    ../../../
    0.14
    åįģ足
    0.11
    åĴ¸
    0.10
    ously
    0.09
    ishly
    0.09
    ues
    0.09
    ç¯ģ
    0.09
    ghi
    0.09
    otle
    0.09
    ä¸Ģç«Ļ
    0.08
    Activations Density 0.006%

    No Known Activations