© 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. 26661
    Prev
    Next
    INDEX
    Explanations

    composers like Mozart and Strauss

    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
    itin
    -0.10
    лив
    -0.09
    à¹Ģà¸īà¸ŀาะ
    -0.09
    à¸ķรà¸ĩ
    -0.09
    纵
    -0.09
    flare
    -0.08
    ãĢħ
    -0.08
     multiline
    -0.08
     добÑĢо
    -0.08
    ilion
    -0.08
    POSITIVE LOGITS
    æĸĽ
    0.09
    èĽ©
    0.09
    matic
    0.09
    atori
    0.08
    loo
    0.08
    ues
    0.08
    ãģĹãģ¾ãģĨ
    0.08
    lander
    0.08
    mate
    0.08
    -handle
    0.08
    Activations Density 0.006%

    No Known Activations