© 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. 22932
    Prev
    Next
    INDEX
    Explanations

    parent, parents, parenting

    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
     Mund
    -0.10
    æķ´ä¸ªäºº
    -0.10
    éĢĢ
    -0.09
    æ¯ı个人éĥ½
    -0.09
     веÑģÑĮ
    -0.09
    ervo
    -0.08
     protocol
    -0.08
     Rx
    -0.08
    妩
    -0.08
    çĻ½èıľ
    -0.08
    POSITIVE LOGITS
    家éķ¿
    0.21
    对åŃ©åŃIJ
    0.19
     parent
    0.19
    çĪ¶æ¯į
    0.19
     Parent
    0.18
    parent
    0.18
    亲åŃIJ
    0.18
     parenting
    0.17
     parents
    0.17
    çĪ¶
    0.17
    Activations Density 0.169%

    No Known Activations