© 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. 35244
    Prev
    Next
    INDEX
    Explanations

    edition

    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
    cade
    -0.09
    ç¿Ķ
    -0.09
    æľĢ容æĺĵ
    -0.09
    æĪIJçĨŁçļĦ
    -0.09
    setIcon
    -0.08
    ply
    -0.08
    管ç½ij
    -0.08
    åī¯ä¼ļéķ¿
    -0.08
    èĴ¿
    -0.08
    ä¸Ģç¬Ķ
    -0.08
    POSITIVE LOGITS
     Lump
    0.10
    trs
    0.09
    edition
    0.09
     edition
    0.08
    imos
    0.08
    Mahon
    0.08
    ä¸ĸçķĮåIJĦåĽ½
    0.08
    ä¸įæĸŃå®ĮåĸĦ
    0.08
     edición
    0.08
    -olds
    0.08
    Activations Density 0.028%

    No Known Activations