© 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. 33666
    Prev
    Next
    INDEX
    Explanations

    references, citations, or specific publication details

    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
    éĥ½åĸľæ¬¢
    -0.09
    åĽ¾ä¸º
    -0.08
    ä¼ļä¸Ĭ
    -0.08
    æį®ç»Łè®¡
    -0.08
    å¢ŀ强äºĨ
    -0.08
    éģĹåĿĢ
    -0.08
    å¯Ħæīĺ
    -0.08
    æĺ¯ä¸Ģ座
    -0.08
     Zak
    -0.07
    被èªī
    -0.07
    POSITIVE LOGITS
    pliant
    0.09
    Ñĩем
    0.08
    顽
    0.08
    __;
    0.08
     зÑĢ
    0.08
    ä»Ģä¹Īåij¢
    0.08
    inality
    0.08
    Looper
    0.08
    aland
    0.08
    аÑĨи
    0.08
    Activations Density 0.587%

    No Known Activations