© 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. 48396
    Prev
    Next
    INDEX
    Explanations

    engineering maintenance and reliability

    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
    羿
    -0.10
    éĢĤåºĶ
    -0.10
    çİ·
    -0.09
    åĢĺ
    -0.09
    å¼Ń
    -0.09
    æĮ¹
    -0.09
    æ³ĵ
    -0.09
    _picker
    -0.08
    èĪªéģĵ
    -0.08
    让æ¶Īè´¹èĢħ
    -0.08
    POSITIVE LOGITS
    æ£Ģä¿®
    0.18
    ä¿Ŀåħ»
    0.18
    ç»´ä¿®
    0.16
    ç»´æĬ¤
    0.15
     maintenance
    0.14
     Maintenance
    0.13
    ä¿®çIJĨ
    0.13
    Maintenance
    0.12
    maintenance
    0.12
    è¿IJç»´
    0.12
    Activations Density 0.245%

    No Known Activations