© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9763
    Prev
    Next
    INDEX
    Explanations

    separate page

    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
    亲èĩª
    -0.09
    ä½łçŁ¥éģĵ
    -0.09
    æħ·
    -0.09
    åĽ½åºĨ
    -0.08
    æ½Ń
    -0.08
    æĮ½
    -0.08
    ä¸Ģéĥ¨
    -0.08
    (ST
    -0.08
    éģĺ
    -0.08
    à¹Ģà¸Ĭ
    -0.08
    POSITIVE LOGITS
     pages
    0.20
     ÑģÑĤÑĢаниÑĨ
    0.19
     page
    0.19
    页éĿ¢
    0.17
    ãĥļãĥ¼ãĤ¸
    0.17
    ä¸Ģ页
    0.16
    页
    0.16
    éłģ
    0.15
     íİĺìĿ´ì§Ģ
    0.15
    åĩłå¼ł
    0.15
    Activations Density 0.217%

    No Known Activations