© 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. 29798
    Prev
    Next
    INDEX
    Explanations

    pole position or pole vault

    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
    ening
    -0.11
    ãģĦãģĨ
    -0.11
    ованиÑı
    -0.10
    niest
    -0.09
    ment
    -0.09
    ners
    -0.09
     gái
    -0.09
    éĽ¢ãĤĮ
    -0.09
    sembl
    -0.08
    ../../../
    -0.08
    POSITIVE LOGITS
     gắng
    0.11
    backs
    0.10
    ç²ķ
    0.10
    æĿĨ
    0.09
    rush
    0.09
    pole
    0.09
     зÑĢениÑı
    0.09
    geist
    0.09
    ÙĨÙħ
    0.09
     ë¶Ī구íķĺê³ł
    0.09
    Activations Density 0.009%

    No Known Activations