© 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. 62511
    Prev
    Next
    INDEX
    Explanations

    most appropriate sufficient tolerated

    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
    è¿Ļä¹Ī说
    -0.11
    ä¸ĩä¸Ģ
    -0.10
    æĩĴå¾Ĺ
    -0.09
    许
    -0.09
    å°±æĺ¯ä¸ºäºĨ
    -0.09
    çħĮ
    -0.09
    æĹłæķ°æ¬¡
    -0.09
    çľĭçľĭ
    -0.09
    ç»Ń
    -0.08
     literally
    -0.08
    POSITIVE LOGITS
     surprisingly
    0.11
    ä¼¼çļĦ
    0.10
    åijĪçİ°åĩº
    0.09
    æĺİæĺ¾
    0.09
    ä½ĵçİ°åĩº
    0.09
    overall
    0.09
    åĪĿæŃ¥
    0.09
    unexpected
    0.08
    ç«Ł
    0.08
     unexpectedly
    0.08
    Activations Density 1.349%

    No Known Activations