© 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. 49362
    Prev
    Next
    INDEX
    Explanations

    idea of

    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
    åģıåģı
    -0.09
    æĪijçŁ¥éģĵ
    -0.09
    è¯Ŀ说
    -0.08
    æĺİç¡®æıIJåĩº
    -0.08
    åijĬè¯ī
    -0.08
    ç»Ĩç»Ĩ
    -0.08
    管线
    -0.08
    ans
    -0.08
    æĪijä»¬çŁ¥éģĵ
    -0.08
    ä½łçŁ¥éģĵ
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåı«
    0.09
     how
    0.09
     Gors
    0.08
    ä»Ģä¹Īæĺ¯
    0.08
    ä¸¤å¼ł
    0.08
    èħ¾é£ŀ
    0.08
    _Cl
    0.08
    ä¸ĢäºĮ
    0.08
     fet
    0.08
    canf
    0.08
    Activations Density 0.046%

    No Known Activations