© 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. 19097
    Prev
    Next
    INDEX
    Explanations

    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
    perf
    -0.09
    æľºåĬ¨
    -0.09
    ะ
    -0.08
    ÙĨس
    -0.08
     Pearce
    -0.08
    afx
    -0.08
    éĢłä»·
    -0.08
    andon
    -0.08
    åݿ级
    -0.08
    æ¯ı个人
    -0.08
    POSITIVE LOGITS
    家éķ¿
    0.15
    èĤ²åĦ¿
    0.14
     parenting
    0.13
    家éķ¿ä»¬
    0.13
    家åºŃæķĻèĤ²
    0.12
    parent
    0.12
    åŃ©åŃIJ
    0.11
     parent
    0.11
     Parent
    0.11
    _parent
    0.11
    Activations Density 0.111%

    No Known Activations