© 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. 2715
    Prev
    Next
    INDEX
    Explanations

    timing and scheduling

    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
    éĢį
    -0.11
    èı½
    -0.11
    yro
    -0.10
    éªĬ
    -0.09
    umbnail
    -0.09
    .MenuItem
    -0.09
    çİ°éĺ¶æ®µ
    -0.09
    æµģ产
    -0.09
    è´¨éĩıåĴĮ
    -0.09
    ç»ĦæĪIJçļĦ
    -0.09
    POSITIVE LOGITS
    å®ļæŶ
    0.11
     timing
    0.11
     schedule
    0.11
    ä»Ģä¹ĪæŶåĢĻ
    0.10
    ä½ķæŶ
    0.10
    .Sync
    0.10
    æĹ¶æľº
    0.10
    å®ļçĤ¹
    0.10
    大èĩ´
    0.09
    schedule
    0.09
    Activations Density 0.129%

    No Known Activations