© 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. 18461
    Prev
    Next
    INDEX
    Explanations

    iPod or iPad

    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
    ane
    -0.08
    éĤ£ä¸ªäºº
    -0.08
    upp
    -0.08
    amen
    -0.08
    æĺ¯ä¸Ģ座
    -0.08
    ixin
    -0.08
    ervo
    -0.08
    æĦİ
    -0.08
    ä¸įåłª
    -0.08
    åģĥ
    -0.08
    POSITIVE LOGITS
    æĪIJ人
    0.10
    gang
    0.10
    lectual
    0.09
    empo
    0.09
    à´±
    0.09
    ừng
    0.09
    婪
    0.08
    IVITY
    0.08
    æĸĩ娱
    0.08
    PING
    0.08
    Activations Density 0.003%

    No Known Activations