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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9516
    Prev
    Next
    INDEX
    Explanations

    numbers and legal/copyright text

    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
    ä»¥äººä¸ºæľ¬
    -0.10
    วาà¸ĩ
    -0.10
    aus
    -0.09
    iren
    -0.09
    æªIJ
    -0.09
    gart
    -0.09
    umann
    -0.09
    ç¼Ł
    -0.09
    æŀķ
    -0.09
    logy
    -0.09
    POSITIVE LOGITS
    æľīæĿ¡ä»¶çļĦ
    0.09
    inters
    0.09
    ä»Ĭ
    0.09
    jin
    0.08
    leigh
    0.08
    å°±è¿ij
    0.08
    /angular
    0.08
    ãĤ¯ãĥĪ
    0.08
    /ay
    0.08
    Sa
    0.08
    Activations Density 0.218%

    No Known Activations