© 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. 35737
    Prev
    Next
    INDEX
    Explanations

    academic programs and subjects

    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
    iasm
    -0.09
    æĪĺæľ¯
    -0.09
    æ°ijèIJ¥
    -0.09
    åĸľæ¬¢åIJĥ
    -0.09
    åģ¥åº·çļĦ
    -0.08
    çŀŁ
    -0.08
    è¹ĭ
    -0.08
    å··
    -0.08
    egis
    -0.08
     лÑİ
    -0.08
    POSITIVE LOGITS
    é¢ĨåŁŁçļĦ
    0.14
    åѦç§ij
    0.12
    é¢ĨåŁŁ
    0.11
    åŀĤ
    0.10
    æĺ¾
    0.09
     discipline
    0.09
    å±ķ
    0.09
    éłĺåŁŁ
    0.09
     discipl
    0.09
     облаÑģÑĤи
    0.08
    Activations Density 0.049%

    No Known Activations