© 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. 51747
    Prev
    Next
    INDEX
    Explanations

    actions with consequences or conditions

    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
    æł¸å®ļ
    -0.09
    apr
    -0.09
    _Internal
    -0.08
    ÃĸZ
    -0.08
    çļĦåIJĦç§į
    -0.08
    èĥ½çľĭåĩº
    -0.08
    çģ¾å®³
    -0.08
    extent
    -0.08
    lear
    -0.08
    ä¸ĬæĿ¥
    -0.08
    POSITIVE LOGITS
    让èĩªå·±
    0.10
    缸å½ĵäºİ
    0.10
    æ½ľåľ¨
    0.10
    æĹłå½¢
    0.10
    äºĨä¸Ģ个
    0.10
    æĥº
    0.10
    篱
    0.10
    æĬĬèĩªå·±çļĦ
    0.10
    æĬĬèĩªå·±
    0.09
    äºĨèĩªå·±çļĦ
    0.09
    Activations Density 0.093%

    No Known Activations