© 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. 24339
    Prev
    Next
    INDEX
    Explanations

    Gibson

    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
    ฤ
    -0.09
    uty
    -0.09
    umu
    -0.08
    idue
    -0.08
    åľ©
    -0.08
    icom
    -0.08
    ×ĺ׾
    -0.08
    aux
    -0.08
    ä¸Ģ线åŁİå¸Ĥ
    -0.08
     æŀ
    -0.08
    POSITIVE LOGITS
    ested
    0.10
    деÑĢ
    0.10
    wright
    0.10
    天涯
    0.10
    ä»Ģä¹Īéĥ½
    0.09
    è¿Ļè¯Ŀ
    0.09
    eler
    0.09
     возд
    0.09
    lé
    0.08
    endale
    0.08
    Activations Density 0.002%

    No Known Activations