© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16936
    Prev
    Next
    INDEX
    Explanations

    single parent, mother, or mama

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    æ¼ł
    -0.21
    åįģåħ«å±Ĭ
    -0.20
    ä¹ĭæĥħ
    -0.19
    æŀ¶åŃIJ
    -0.18
    vak
    -0.18
    æľīåħ³éĥ¨éŨ
    -0.18
     kone
    -0.18
     бÑĥк
    -0.18
    å°±ä¸įèĥ½
    -0.18
    ä¾ĽéľĢ
    -0.18
    POSITIVE LOGITS
    家åºŃ
    0.21
     каÑĩ
    0.19
    fant
    0.19
    _unpack
    0.19
    æĴij
    0.19
    mons
    0.18
     Noel
    0.18
    å¸
    0.18
    licable
    0.18
    æĬļåħ»
    0.18
    Activations Density 0.008%

    No Known Activations