© 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. 38056
    Prev
    Next
    INDEX
    Explanations

    supermarket, store, convenience

    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
    说åĩºæĿ¥
    -0.11
    åıĺåİĭ
    -0.10
    TED
    -0.10
    éĿŀçī©è´¨
    -0.10
    ç»ı纪
    -0.10
    æľīå¾Īå¤ļç§į
    -0.10
    åIJģ
    -0.09
    æĻ¯å¾·
    -0.09
    缨
    -0.09
    éĻĮ
    -0.09
    POSITIVE LOGITS
    便åĪ©åºĹ
    0.10
     grocery
    0.10
    è¶ħå¸Ĥ
    0.10
    快讯
    0.10
    4
    0.09
     shelves
    0.09
     Convenience
    0.09
    Clone
    0.09
     groceries
    0.09
    æĮ½
    0.09
    Activations Density 0.087%

    No Known Activations