© 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. 23176
    Prev
    Next
    INDEX
    Explanations

    opponents and schedule

    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
    纪
    -0.10
    è¡°
    -0.09
    æŀIJ
    -0.09
    ç´Ģ
    -0.09
    访
    -0.08
    欣
    -0.08
    ä¸įäºĨ
    -0.08
    æĽĻ
    -0.08
    bare
    -0.08
    æľªç»ı
    -0.08
    POSITIVE LOGITS
    æķĻèģĮå·¥
    0.10
     ÑĦакÑĤ
    0.09
    æį®
    0.09
    éºĭ
    0.09
    ippers
    0.09
    æ½®
    0.09
    ERGY
    0.08
    asher
    0.08
    боÑĤ
    0.08
    odi
    0.08
    Activations Density 0.007%

    No Known Activations