© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20693
    Prev
    Next
    INDEX
    Explanations

    outdoor recreational activities

    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
    å¾Ģå¾Ģä¼ļ
    -0.10
    owner
    -0.09
    isse
    -0.09
    ä¸Ģç±»
    -0.09
    -nav
    -0.08
     vez
    -0.08
    åĪĩéĻ¤
    -0.08
    ãģ§ãģ¯ãģªãģı
    -0.08
    olan
    -0.08
    eneral
    -0.08
    POSITIVE LOGITS
     opportunities
    0.15
    çļĦæľºä¼ļ
    0.13
    æľºä¼ļ
    0.13
     Opportunities
    0.11
     opportunity
    0.11
    åı¯ä¾Ľ
    0.11
    æ©Łæľĥ
    0.10
    ç»ķ
    0.09
    UNET
    0.09
    黯
    0.09
    Activations Density 0.040%

    No Known Activations