© 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. 49703
    Prev
    Next
    INDEX
    Explanations

    Premier League or Premiership football

    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
    éĬ®
    -0.10
    å¢ī
    -0.10
    é¬ĵ
    -0.09
    大åѦæ¯ķä¸ļ
    -0.08
    èķī
    -0.08
    åħ¬ç§¯
    -0.08
    常年
    -0.08
    ements
    -0.08
    ifice
    -0.08
     pens
    -0.08
    POSITIVE LOGITS
    çİ°æľī
    0.10
    .Features
    0.09
    æīĵå¾Ĺ
    0.09
    èĩ³ä»Ĭ
    0.09
    vo
    0.09
    缮åīįå·²
    0.08
    æ°´åĪ©å·¥ç¨ĭ
    0.08
    å®īåħ¨ä¿Ŀéļľ
    0.08
     GANG
    0.08
    æ³¥
    0.08
    Activations Density 0.029%

    No Known Activations