© 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. 63373
    Prev
    Next
    INDEX
    Explanations

    for you

    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
    è´¼
    -0.08
    uded
    -0.08
    人为
    -0.08
    åIJ¹
    -0.08
     trivial
    -0.08
    à¸Ħà¸ĩ
    -0.08
    æĮª
    -0.08
    기를
    -0.07
    Nom
    -0.07
     sud
    -0.07
    POSITIVE LOGITS
    çİ°éĺ¶æ®µ
    0.13
    åĽ½æĥħ
    0.12
    å®ŀéĻħæĥħåĨµ
    0.11
    è¿Ļç§įæĥħåĨµ
    0.10
    ä»İèĢĮ使
    0.10
    æĥħåĨµ
    0.10
    rary
    0.10
    çİ°æľī
    0.10
    çļĦæĥħåĨµ
    0.09
    å·¥åķĨå±Ģ
    0.09
    Activations Density 0.059%

    No Known Activations