© 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. 32588
    Prev
    Next
    INDEX
    Explanations

    location words and roles

    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
    oris
    -0.09
     advers
    -0.08
    è¿Ļç¯ĩæĸĩç«ł
    -0.08
    é³ŀ
    -0.08
    平稳
    -0.08
    Bur
    -0.08
    äºĨå¾Īå¤ļ
    -0.08
     burial
    -0.08
    éĩijéĻµ
    -0.07
    gars
    -0.07
    POSITIVE LOGITS
    æĪIJåijĺ
    0.10
    åıĤä¸İèĢħ
    0.09
    ä¸ĢæĹ¥
    0.09
    ç¥ŀä»Ļ
    0.09
    é¹Ĭ
    0.09
     members
    0.09
    æľįåĬ¡æ°´å¹³
    0.09
    æĪIJåijĺåįķä½į
    0.09
    å¸ĥæľĹ
    0.09
    壮大
    0.09
    Activations Density 0.444%

    No Known Activations