© 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. 7570
    Prev
    Next
    INDEX
    Explanations

    aged or other descriptors

    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
    ба
    -0.09
    _rights
    -0.09
    é«ĺçŃī
    -0.09
    олÑı
    -0.08
    æĹłæķ°æ¬¡
    -0.08
    ноп
    -0.08
    childs
    -0.08
     عدة
    -0.08
    бал
    -0.08
    ìŀIJìĿĺ
    -0.08
    POSITIVE LOGITS
    符åIJĪæĿ¡ä»¶
    0.12
    åĿĩåı¯
    0.10
     eligible
    0.10
    ä¸įå°ijäºİ
    0.10
    èĩ³å°ij
    0.10
    æīĢåľ¨çļĦ
    0.10
    ä¸įè¶ħè¿ĩ
    0.09
     preferably
    0.09
    Å¡ÃŃ
    0.09
    ksen
    0.09
    Activations Density 0.177%

    No Known Activations