© 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. 18016
    Prev
    Next
    INDEX
    Explanations

    aims, goals, or mission

    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
    èł
    -0.10
    éĤ¯
    -0.09
    设æĸ½å»ºè®¾
    -0.09
    æĸ°éĹ»è®°èĢħ
    -0.09
    å¤ĸè¯Ń
    -0.09
    çijĹ
    -0.09
    çŃīå½¢å¼ı
    -0.09
    é¾Ľ
    -0.09
    æĻ¯è§Ĥ
    -0.08
    çļĦè¯Ńè¨Ģ
    -0.08
    POSITIVE LOGITS
     eventual
    0.09
     vision
    0.09
     Vision
    0.09
    大èĩ´
    0.08
    anus
    0.08
    å®ıä¼Ł
    0.08
     stated
    0.08
    ç¶
    0.08
    ange
    0.08
    urus
    0.07
    Activations Density 0.044%

    No Known Activations