© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12330
    Prev
    Next
    INDEX
    Explanations

    all or everything

    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
    Negative Logits
    å¾Īç®Ģåįķ
    -0.10
    urr
    -0.09
    isters
    -0.09
    æ±īè¯Ń
    -0.09
    ä¼łéĢĴ
    -0.09
    éĻIJå®ļ
    -0.09
     indef
    -0.09
    edom
    -0.08
    说ä¸įå®ļ
    -0.08
    emode
    -0.08
    POSITIVE LOGITS
    æĹłæīĢ
    0.10
    å°Ŀ
    0.10
    æŀģ端
    0.10
    å§Ĵ
    0.09
    types
    0.09
    ç±»åŀĭçļĦ
    0.09
    ç¼Ķ
    0.09
     imaginable
    0.09
    ãģĻãģ¹
    0.08
     nose
    0.08
    Activations Density 0.062%

    No Known Activations