© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38340
    Prev
    Next
    INDEX
    Explanations

    Diaz, daisy, Gatsby, diazepam

    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
    è¿ĻçĤ¹
    -0.10
    è´¢
    -0.09
    éĴ»çłĶ
    -0.09
    à¹ģà¸Ħ
    -0.08
    ãĤį
    -0.08
     ado
    -0.08
    è¿Ļä¸ĢçĤ¹
    -0.08
    ament
    -0.08
    å¾Ĺ好
    -0.08
     Hond
    -0.08
    POSITIVE LOGITS
    coin
    0.09
    deen
    0.09
    hood
    0.08
    /column
    0.08
    çľ
    0.08
     ÑĢейÑĤинг
    0.08
     perfection
    0.08
    dale
    0.08
    èıĩ
    0.08
    æł·çļĦ
    0.08
    Activations Density 0.006%

    No Known Activations