© 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. 2611
    Prev
    Next
    INDEX
    Explanations

    is there a way to

    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
    æīĢéľĢè¦ģçļĦ
    -0.09
    hiro
    -0.09
    æĸ°çļĦä¸Ģ
    -0.09
    人æ°ijæľįåĬ¡
    -0.09
    çĽİ
    -0.08
     ngũ
    -0.08
     targetType
    -0.08
    å¾ģæľį
    -0.08
    notation
    -0.08
    DBObject
    -0.08
    POSITIVE LOGITS
    ä¸įéĢļ
    0.10
    åīįåIJİ
    0.10
    æµİ
    0.10
    æݥ触åĪ°
    0.10
    æ½®
    0.10
    ä¸įç»ı
    0.10
    åIJĥåĪ°
    0.09
     dosage
    0.09
    å°ıå¾®
    0.09
     ward
    0.09
    Activations Density 0.100%

    No Known Activations