© 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. 11105
    Prev
    Next
    INDEX
    Explanations

    caring, compassionate, loving

    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
    çİ
    -0.20
    污æŁĵéĺ²æ²»
    -0.19
     droit
    -0.18
    éĺ´è°ĭ
    -0.18
    æĪĺæľº
    -0.18
    åļ£
    -0.18
    çݯå¢ĥ污æŁĵ
    -0.18
    èĻ¾
    -0.18
    è¿Ŀæ³ķ
    -0.18
    å¼¹
    -0.17
    POSITIVE LOGITS
     caring
    0.24
    ä½ĵè´´
    0.23
    åħ³æĢĢ
    0.23
    对å¾ħ
    0.22
    åħ³çĪ±
    0.22
    æģ»
    0.21
    æģ¤
    0.20
    ä¹ĭå¿ĥ
    0.19
    åijµæĬ¤
    0.19
     care
    0.19
    Activations Density 0.024%

    No Known Activations