© 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. 2851
    Prev
    Next
    INDEX
    Explanations

    parents and parenthood

    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
    æĸ½å±ķ
    -0.10
    æ´»åĬ¨çİ°åľº
    -0.09
    åIJĥäºĨ
    -0.09
    éªļæī°
    -0.09
    éĤ£æ¬¡
    -0.09
    ä¸ĢæŃ¥æŃ¥
    -0.09
    æīĵæī°
    -0.09
    æŀ«
    -0.09
    羦
    -0.08
    æ²IJæµ´
    -0.08
    POSITIVE LOGITS
    家éķ¿
    0.13
    thood
    0.13
    parent
    0.10
     parent
    0.10
    -parent
    0.10
    为人
    0.10
    paren
    0.10
     Parent
    0.09
    家éķ·
    0.09
    getParent
    0.09
    Activations Density 0.100%

    No Known Activations