© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19730
    Prev
    Next
    INDEX
    Explanations

    household chores and tasks

    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
    ibur
    -0.09
    è¿Ļç§įæĸ¹æ³ķ
    -0.09
    éĢ¢
    -0.09
    ä¸ĵçĶ¨
    -0.09
    èĥĨ
    -0.09
    ppy
    -0.09
     lãi
    -0.09
     бил
    -0.09
     olacaģı
    -0.09
     ÑģÑĤÑĢа
    -0.09
    POSITIVE LOGITS
    家åĬ¡
    0.20
     tasks
    0.15
     chores
    0.13
    ç¹ģ
    0.12
    åĬ³åĬ¨
    0.11
    tasks
    0.11
    æ´Ĺè¡£
    0.11
    äºĭåĬ¡
    0.11
    Tasks
    0.11
    ä»»åĬ¡
    0.11
    Activations Density 0.214%

    No Known Activations