© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16868
    Prev
    Next
    INDEX
    Explanations

    primary constituent, funding, function, aim, role

    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
    èĶ¼
    -0.11
    ery
    -0.11
    ervo
    -0.10
    æ®į
    -0.10
    icher
    -0.09
    اÙħÙĦ
    -0.09
    ening
    -0.09
    âľķ
    -0.09
    ation
    -0.09
    ibel
    -0.09
    POSITIVE LOGITS
    ìłģìľ¼ë¡ľ
    0.13
    mente
    0.12
    åİŁåĽłæĺ¯
    0.10
    atic
    0.10
    ordial
    0.10
    责任人
    0.09
    ìłģìĿ¸
    0.09
    ogy
    0.09
    Çİ
    0.09
    åħ³æ³¨
    0.09
    Activations Density 0.031%

    No Known Activations