© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35542
    Prev
    Next
    INDEX
    Explanations

    food items and drinks

    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
    ÑĥÑĩ
    -0.09
    éĬ®
    -0.09
    ãģ¡ãģ¯
    -0.09
     Ñģл
    -0.08
    æ³ķå®Ŀ
    -0.08
    ðŁĶĢ
    -0.08
    éģIJ
    -0.08
    веÑģ
    -0.08
    缸åºĶ
    -0.08
    æī¿æİ¥
    -0.08
    POSITIVE LOGITS
    klass
    0.09
    IDADE
    0.09
    æĸ¯åŁº
    0.08
    åĨįä¹Łä¸į
    0.08
    鼶è·Ŀ离
    0.08
    åįĸç»Ļ
    0.08
    满满çļĦ
    0.08
    çĿ¹
    0.08
    CRE
    0.08
    ór
    0.08
    Activations Density 0.072%

    No Known Activations