© 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. 22562
    Prev
    Next
    INDEX
    Explanations

    so much, more, enough

    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
    ÑĢей
    -0.10
    åŀ¦
    -0.09
    inger
    -0.09
    æ¯Ļ
    -0.09
    æ¼Ĥæµģ
    -0.09
    è²Į
    -0.09
    å®ļåIJij
    -0.09
    èIJ¸
    -0.09
    溯
    -0.09
    漯
    -0.09
    POSITIVE LOGITS
    ä¹Łæĺ¯å¦ĤæѤ
    0.14
     ones
    0.12
     thereof
    0.11
    ones
    0.11
    éĤ£æł·
    0.10
    utow
    0.10
    å¦ĤæѤ
    0.10
     so
    0.10
     alike
    0.10
    çļĦéĤ£ç§į
    0.09
    Activations Density 0.090%

    No Known Activations