© 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. 62114
    Prev
    Next
    INDEX
    Explanations

    hours per day

    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
    åľ¨æķ´ä¸ª
    -0.09
    ynch
    -0.09
    åħ¬çĦ¶
    -0.09
     Pist
    -0.09
    å·¥å§Ķ
    -0.08
    oeff
    -0.08
    æľ¨è´¨
    -0.08
    .lb
    -0.08
    .Request
    -0.08
     fron
    -0.08
    POSITIVE LOGITS
    æ¯ıæĹ¥
    0.12
    æĺ±
    0.12
    æ¯ı天
    0.11
    ä¸įå°ijäºİ
    0.11
    æ¼ķ
    0.11
    æĻ¨
    0.10
     daily
    0.10
    ç»ĥä¹ł
    0.10
    天天
    0.10
    daily
    0.10
    Activations Density 0.056%

    No Known Activations