© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 52262
    Prev
    Next
    INDEX
    Explanations

    news outlet reports

    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
    agos
    -0.10
    é£İ
    -0.09
    Ãło
    -0.09
    æłı
    -0.09
    æľįåĬ¡åĮº
    -0.09
    멸
    -0.09
    çļĦéĤ£ç§į
    -0.09
    åĸĥ
    -0.09
    çε士
    -0.09
    aan
    -0.09
    POSITIVE LOGITS
    è°ĥæŁ¥æĺ¾ç¤º
    0.10
    ä¸Ģç¯ĩæĸĩ竳
    0.10
    ä¸Ĭåij¨
    0.09
     recently
    0.09
    æĬĬè¿Ļ个
    0.08
    ä¹±
    0.08
    好å¥ĩ
    0.08
    æİ¥åΰ
    0.08
    æľ¬åij¨
    0.08
    触åıĬ
    0.08
    Activations Density 0.073%

    No Known Activations