© 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. 10735
    Prev
    Next
    INDEX
    Explanations

    will/would know what next

    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
    åºĶéĤĢ
    -0.09
    __.__
    -0.09
    åĢ¦
    -0.08
    åĽ½æ°ij
    -0.08
    çĥŃéĩı
    -0.08
    èħIJ
    -0.08
    æĻ¯
    -0.08
    溲
    -0.08
    æ±Ĺæ°´
    -0.08
    ä¸įçĶ¨æĭħå¿ĥ
    -0.08
    POSITIVE LOGITS
    å®ļä»·
    0.10
    èĩ¾
    0.10
    æĦıæĢĿ
    0.10
    ä¹Łä¸įæĥ³
    0.09
    ä¸Ģä¼ļ
    0.09
    enville
    0.09
    å·Ŀ
    0.09
    ses
    0.08
    ä¸įåı¯ä»¥
    0.08
    éĤ¬
    0.08
    Activations Density 0.033%

    No Known Activations