© 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. 31415
    Prev
    Next
    INDEX
    Explanations

    names and schools

    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
    ham
    -0.08
    没人
    -0.08
    isi
    -0.08
    arat
    -0.08
    lessly
    -0.08
    o
    -0.08
    isor
    -0.08
     vigor
    -0.08
     part
    -0.08
    ä¿ij
    -0.08
    POSITIVE LOGITS
    tings
    0.11
     же
    0.10
    alytics
    0.10
     nhiên
    0.10
    们éĥ½
    0.10
    /XMLSchema
    0.10
    amarin
    0.10
    ìłĦìŀIJ
    0.09
    .nlm
    0.09
    acles
    0.09
    Activations Density 0.006%

    No Known Activations