© 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. 39143
    Prev
    Next
    INDEX
    Explanations

    schedule and planning

    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
     напÑĢавлен
    -0.09
    å®ļåIJij
    -0.09
    aho
    -0.08
    ongo
    -0.08
    ulan
    -0.08
    è´¬
    -0.08
    ç»®
    -0.08
    ç»ĵå®ŀ
    -0.08
    éħĴç²¾
    -0.08
    èĪ¹ä¸Ĭ
    -0.08
    POSITIVE LOGITS
     schedule
    0.22
    å®īæİĴ
    0.19
     schedules
    0.19
    schedule
    0.18
     Schedule
    0.18
     scheduling
    0.17
    è°ĥ度
    0.16
    (schedule
    0.16
    Schedule
    0.15
     sched
    0.15
    Activations Density 0.108%

    No Known Activations