© 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. 32964
    Prev
    Next
    INDEX
    Explanations

    taking action or measures

    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
     laure
    -0.10
    urance
    -0.10
    殿ä¸ĭ
    -0.09
    à¸ģารà¸Ĺำà¸ĩาà¸Ļ
    -0.09
    ги
    -0.09
    amic
    -0.09
    漫éķ¿
    -0.09
    wik
    -0.09
    ä¸īæľŁ
    -0.08
    çĤķ
    -0.08
    POSITIVE LOGITS
    æݪæĸ½
    0.11
    łéĻ¤
    0.10
     пÑĢедоÑģÑĤ
    0.09
    ÑĤал
    0.09
    迹象
    0.08
    è¡ĮåĬ¨
    0.08
    emean
    0.08
    ложений
    0.08
    IENT
    0.08
    igits
    0.08
    Activations Density 0.024%

    No Known Activations