© 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. 30252
    Prev
    Next
    INDEX
    Explanations

    cookies or files stored

    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
    æijĨ
    -0.11
    ä¸Ģ人
    -0.09
    icht
    -0.09
    ë´ī
    -0.09
    ç«¥
    -0.09
    æĵº
    -0.09
    æŃ£åľ¨è¿Ľè¡Į
    -0.09
    æŃ£åľ¨
    -0.09
     Bott
    -0.09
    PEC
    -0.09
    POSITIVE LOGITS
    å¾Īå°ı
    0.08
     Alma
    0.08
     IE
    0.08
    çŃ¾è¯ģ
    0.08
    çľĩ
    0.08
     Hoffman
    0.08
    éķ¿å¤§
    0.08
    æĬ¤çħ§
    0.08
    ny
    0.08
     Osw
    0.08
    Activations Density 0.020%

    No Known Activations