© 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. 31272
    Prev
    Next
    INDEX
    Explanations

    piezoelectricity, photovoltaic, voltain

    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
    pu
    -0.10
    æ°´éĩı
    -0.09
    å®ŀ
    -0.09
    人为
    -0.08
    pen
    -0.08
    æ¯Ķäºļ
    -0.08
    åĽ¢è´Ń
    -0.08
    èIJ¥éĢł
    -0.08
    ieu
    -0.08
    ä¹Łä¸įè¦ģ
    -0.08
    POSITIVE LOGITS
    æĸ¹æīį
    0.10
    å·¥ä½ľæķĪçİĩ
    0.10
     pie
    0.10
    ovolta
    0.10
    çł´
    0.09
    æĪ¿åŃIJ
    0.09
    转æį¢
    0.09
     convert
    0.09
    beck
    0.09
    çķĻè¨ĢæĿ¿
    0.09
    Activations Density 0.132%

    No Known Activations