© 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. 7447
    Prev
    Next
    INDEX
    Explanations

    Do you want to

    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
     некоÑĤоÑĢ
    -0.09
    .ga
    -0.09
    津贴
    -0.09
    ç²²
    -0.09
    çħ
    -0.09
    æ©¡
    -0.08
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.08
    ÑĩаÑĤ
    -0.08
    dee
    -0.08
    æĽ´å®¹æĺĵ
    -0.08
    POSITIVE LOGITS
    æĦ¿æĦı
    0.13
    è¦ģä¸įè¦ģ
    0.10
    æĺ¯åIJ¦
    0.09
    åIJĪéĢĤ
    0.09
    orns
    0.09
     wish
    0.09
    esson
    0.09
     ÑħоÑĤиÑĤе
    0.09
    èĩªæĦ¿
    0.09
    é¡ĺæĦı
    0.09
    Activations Density 0.058%

    No Known Activations