© 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. 27715
    Prev
    Next
    INDEX
    Explanations

    `rails_helper` `/GPL` Wi-Fi

    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
    è³ĩ
    -0.09
    aki
    -0.09
    Gram
    -0.09
    Arch
    -0.09
    ÑĥлÑĮÑĤ
    -0.08
    Soft
    -0.08
    aryl
    -0.08
    æ°§æ°Ķ
    -0.08
    ours
    -0.08
    leen
    -0.08
    POSITIVE LOGITS
    åºĦ
    0.11
    éĢı
    0.10
    éĽķ
    0.09
    æľ¬ç«Ļ
    0.09
    æĶĢ
    0.09
    æī¯
    0.09
    ackle
    0.09
    æĢ»çIJĨ
    0.08
    alse
    0.08
    åĸ·
    0.08
    Activations Density 0.002%

    No Known Activations