© 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. 51744
    Prev
    Next
    INDEX
    Explanations

    wasted time

    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
    åIJĵå¾Ĺ
    -0.10
     Geb
    -0.09
     меÑģÑıÑĨ
    -0.09
    ummings
    -0.09
    æĬµæĮ¡
    -0.09
    æ°Ĺãģ«
    -0.09
    uese
    -0.08
     Mell
    -0.08
    Sensitive
    -0.08
    ä¸įå®ļ
    -0.08
    POSITIVE LOGITS
     wasted
    0.13
    浪费
    0.13
    èĬ±äºĨ
    0.12
     wasting
    0.12
     waste
    0.11
    èĢ½è¯¯
    0.11
    å®Ŀè´µ
    0.10
    ç²²
    0.10
    èĬ±è´¹
    0.10
    è¾Ľ
    0.10
    Activations Density 0.048%

    No Known Activations