© 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. 8287
    Prev
    Next
    INDEX
    Explanations

    more recently

    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
    æĢ»
    -0.09
    ãģ¨ãģĦãģĨãģ®ãģ¯
    -0.09
    ä¸įéĢļ
    -0.08
    Start
    -0.08
    ç¥ĿæĦ¿
    -0.08
    åį´ä¸į
    -0.08
    æݾ
    -0.08
    好åIJĹ
    -0.08
     Start
    -0.08
    Äĥm
    -0.08
    POSITIVE LOGITS
    isé
    0.10
    女åŃ©åŃIJ
    0.10
    æĽ´éĩįè¦ģçļĦ
    0.09
    å¸ļ
    0.09
    æħİ
    0.09
     Extreme
    0.09
    esign
    0.09
    æĥħåĨµä¸ĭ
    0.09
     sẵ
    0.09
    ساء
    0.08
    Activations Density 0.181%

    No Known Activations