© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7890
    Prev
    Next
    INDEX
    Explanations

    and other

    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
    aldi
    -0.10
    scar
    -0.09
    æķ´ä¸ª
    -0.09
     dabei
    -0.09
    uve
    -0.09
    æĸ¼æĺ¯
    -0.09
    éĢĢä¼ij
    -0.09
    éĩijçīĮ
    -0.09
    .Operator
    -0.09
    çݯçIJĥ
    -0.09
    POSITIVE LOGITS
    gross
    0.11
    èĩ´å¯Į
    0.09
    ç¨įç¨į
    0.09
    çļĦæľĢåIJİä¸Ģ
    0.09
    ç§įç§į
    0.09
    å¹ħ
    0.08
    iner
    0.08
    åĬ¼
    0.08
    лож
    0.08
     minor
    0.08
    Activations Density 0.016%

    No Known Activations