© 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. 30877
    Prev
    Next
    INDEX
    Explanations

    worth it

    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æīĭ
    -0.10
    æĭĴ
    -0.09
    æİĴæĸ¥
    -0.09
    ä¸įåģľçļĦ
    -0.09
    éĿ¢è²Į
    -0.09
    交æİ¥
    -0.09
    æ·±åĪ»çļĦ
    -0.08
    æµı
    -0.08
    ç»
    -0.08
     pitch
    -0.08
    POSITIVE LOGITS
     worth
    0.22
    åĢ¼å¾Ĺä¸Ģ
    0.22
    åĢ¼å¾Ĺ
    0.20
     Worth
    0.20
    worth
    0.19
     worthwhile
    0.18
     ÑģÑĤоиÑĤ
    0.13
    åĢ¼å¾Ĺåħ³æ³¨
    0.13
    æľīä»·åĢ¼çļĦ
    0.12
     ê°Ģì¹ĺ
    0.12
    Activations Density 0.040%

    No Known Activations