© 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. 33774
    Prev
    Next
    INDEX
    Explanations

    in [noun/field]

    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
    é«ĺ度éĩįè§Ĩ
    -0.08
    èĿĩ
    -0.08
    agraph
    -0.08
    nam
    -0.07
    æĮ¡ä½ı
    -0.07
    arry
    -0.07
    /mit
    -0.07
    éıĸ
    -0.07
    æľĢåIJİ
    -0.07
    apa
    -0.07
    POSITIVE LOGITS
    ç»ıå¼Ģ
    0.10
    æĪijä¸Ģ缴
    0.09
    忧
    0.09
     multit
    0.09
    çīĪæĿĥå½Ĵ
    0.09
    ãĤħ
    0.09
    hek
    0.09
    æ²Ļé¾Ļ
    0.09
     PIT
    0.09
     Dum
    0.09
    Activations Density 0.033%

    No Known Activations