© 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. 16898
    Prev
    Next
    INDEX
    Explanations

    Housewives or wife

    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
    éģij
    -0.20
     wholes
    -0.19
    ocard
    -0.19
    åģİ
    -0.19
    ungi
    -0.19
     ÑģамоÑģÑĤоÑı
    -0.19
    opsis
    -0.19
    otec
    -0.18
    æŶæĬ¥
    -0.18
     tán
    -0.18
    POSITIVE LOGITS
    tv
    0.21
    ä¹ĭéģĵ
    0.21
    èĽİ
    0.19
    anza
    0.19
    é¦ĸä½į
    0.18
    ä¸Ģéĥ¨
    0.18
    anghai
    0.18
    yr
    0.18
    èģĬèģĬ
    0.17
     á»ķ
    0.17
    Activations Density 0.003%

    No Known Activations