© 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. 30616
    Prev
    Next
    INDEX
    Explanations

    time of year

    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
    åĮ®
    -0.09
    åĩ¼
    -0.09
    å±Ĭ
    -0.09
    æĽ°
    -0.09
    åĵªæĢķæĺ¯
    -0.08
    caff
    -0.08
    åħĨ
    -0.08
    é£
    -0.08
    оÑĩ
    -0.08
    ToInt
    -0.08
    POSITIVE LOGITS
    å·²ç»ıæĺ¯
    0.10
    人们对
    0.08
    äºĨ
    0.08
    ä»Ģä¹Īäºĭæĥħ
    0.08
    ä¸įåĨįæĺ¯
    0.08
    æĹĮ
    0.08
     therefore
    0.08
    exampleInputEmail
    0.08
    åķĸ
    0.08
    æĿ¯
    0.08
    Activations Density 0.042%

    No Known Activations