© 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. 12014
    Prev
    Next
    INDEX
    Explanations

    sections, course, valley, riders, optoporation, MasterPlayer

    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
    éłĺ
    -0.09
    é¢Ĩ
    -0.08
    ç½ij绾å®īåħ¨
    -0.08
    pper
    -0.08
    åıĤ
    -0.08
    å¿ĥè¡Ģ
    -0.08
    æŀķ头
    -0.08
    èĺ¸
    -0.08
    æ¼ł
    -0.08
    詳
    -0.08
    POSITIVE LOGITS
    åħ¨éķ¿
    0.11
     forgiving
    0.10
    åľ°å½¢
    0.10
     зÑĢ
    0.09
    èĢĥéªĮ
    0.09
    éļIJèĶ½
    0.09
    路段
    0.09
     terrain
    0.09
    éĻ¡
    0.09
    åħ¨ç¨ĭ
    0.09
    Activations Density 0.189%

    No Known Activations