© 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. 59243
    Prev
    Next
    INDEX
    Explanations

    Culver or Calvert

    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
    otec
    -0.09
    åĽ´è§Ĥ
    -0.09
    èĪŀ
    -0.08
    èIJĮ
    -0.08
    åIJĮç±»
    -0.08
    yers
    -0.08
    vak
    -0.08
    è£Ķ
    -0.08
    ergy
    -0.08
     Rout
    -0.08
    POSITIVE LOGITS
    ä¸Ńä»ĭæľºæŀĦ
    0.09
    è¯įæĿ¡
    0.09
    åı¹æģ¯
    0.09
    çķĻè¨Ģ
    0.09
    ä½Ĺ
    0.09
    Ĭ
    0.09
    озв
    0.08
    è¯ĬæĸŃ
    0.08
    稣
    0.08
    ç»Ģ
    0.08
    Activations Density 0.002%

    No Known Activations