© 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. 48225
    Prev
    Next
    INDEX
    Explanations

    scheduling events and appointments

    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
    egr
    -0.10
    åĮħåĮħ
    -0.10
    cheme
    -0.09
    ÑĢÑĥд
    -0.09
    edores
    -0.09
    设计æĸ¹æ¡Ī
    -0.09
    騰
    -0.09
    establish
    -0.09
    ÑĨа
    -0.09
    oute
    -0.09
    POSITIVE LOGITS
    prep
    0.10
    äºĨ个
    0.09
    éĢĢ
    0.09
    æѤ类
    0.09
    åĿļå®ŀçļĦ
    0.09
    åĽĽèĤ¢
    0.08
    èĬ¸
    0.08
    äºĨä¸Ģåľº
    0.08
    æĹ©æĹ¥
    0.08
    åĩºæ¸¸
    0.08
    Activations Density 0.028%

    No Known Activations