© 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. 62227
    Prev
    Next
    INDEX
    Explanations

    Pakistani regions and tribes

    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
    åºIJ
    -0.10
    æIJģ
    -0.09
    çij
    -0.08
    erp
    -0.08
     Bos
    -0.08
    æĺİæĺİ
    -0.08
    icer
    -0.08
    æ¸ļ
    -0.08
    殿åłĤ
    -0.08
    ä¸Ńæŀ¢
    -0.08
    POSITIVE LOGITS
    åľ°å¸¦
    0.10
    åĬ¨åijĺ
    0.10
    éĥİ
    0.09
    á»ĵn
    0.09
    éĢĬ
    0.09
    itsu
    0.09
    éļĺ
    0.09
    éĿ´
    0.09
    蹩
    0.09
    æĹıèĩªæ²»åİ¿
    0.09
    Activations Density 0.016%

    No Known Activations