© 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. 34147
    Prev
    Next
    INDEX
    Explanations

    wrapping or attaching items

    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
    imid
    -0.11
    .bs
    -0.10
    æĸ°çļĦä¸Ģå¹´
    -0.10
    èµ°äºĨ
    -0.10
    æľīéĻIJ责任
    -0.10
    ä¸ĩ个
    -0.10
    aub
    -0.10
    çļĦä¸ĢåĪĩ
    -0.10
     Learned
    -0.09
    çĶļ
    -0.09
    POSITIVE LOGITS
     дополниÑĤелÑĮно
    0.10
    ãģĹãģ¦ãģĬãģı
    0.09
    é¢Ŀå¤ĸ
    0.09
     extra
    0.09
    ä¸ĢäºĽ
    0.09
    äºĭåħĪ
    0.09
    extra
    0.09
    ä¸Ģå°ı
    0.08
    ä¸įå½±åĵį
    0.08
    åį±å®³
    0.08
    Activations Density 0.237%

    No Known Activations