© 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. 1566
    Prev
    Next
    INDEX
    Explanations

    license file accompanying

    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
     zwar
    -0.11
    ä¸įåıªæĺ¯
    -0.10
    èĢĮä¸Ķè¿ĺ
    -0.09
    ãģłãģijãģ§ãģªãģı
    -0.09
    ë¿IJë§Į
    -0.09
    èĢĮä¸Ķ
    -0.09
    æĪĸèĢħ说
    -0.09
    ä¸įåĨįæĺ¯
    -0.09
    ohl
    -0.08
    ilor
    -0.08
    POSITIVE LOGITS
    å¹²èĦĨ
    0.13
    æľ¬èº«å°±æĺ¯
    0.12
    æľ¬èº«çļĦ
    0.11
    æŁIJ个
    0.10
    æĢ»ä¹ĭ
    0.10
    ä¹Łåı¯
    0.10
    ä¹Łåı¯ä»¥
    0.10
    åľ¨ä¸ĢæĹģ
    0.09
    æľ¬èº«å°±
    0.09
    åıįæŃ£
    0.09
    Activations Density 0.250%

    No Known Activations