© 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. 10878
    Prev
    Next
    INDEX
    Explanations

    elderly and older people

    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
    æĢ»çĽij
    -0.20
    å¤Ħåľ¨
    -0.20
    çħĮ
    -0.20
    èIJ¥éĢłèī¯å¥½
    -0.19
    ä¼Ļä¼´
    -0.18
    isky
    -0.18
    è°®
    -0.18
    åĩºåĩ»
    -0.18
    è¾ĵåįµ
    -0.17
    inent
    -0.17
    POSITIVE LOGITS
    èĢģ人
    0.34
    èĢģ太太
    0.29
    -fashioned
    0.28
    èĢĦ
    0.24
    èĢģ年人
    0.24
    éĢĢä¼ij
    0.23
    奶奶
    0.23
    èĢģ人家
    0.22
    èĢģ
    0.22
    èĢģ头
    0.21
    Activations Density 0.082%

    No Known Activations