© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12515
    Prev
    Next
    INDEX
    Explanations

    emotional support

    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
    ç«ŀäºī
    -0.30
    çļĦç«ŀäºī
    -0.30
    产éĩı
    -0.29
    è´¸æĺĵ
    -0.29
    çŀŃ解並
    -0.28
    ç«ŀäºī对æīĭ
    -0.27
    å¢ŀéķ¿çİĩ
    -0.27
     salopes
    -0.27
    æĪIJåĵģ
    -0.26
    çĶŁäº§åĴĮ
    -0.25
    POSITIVE LOGITS
     compassion
    0.31
     empath
    0.27
     stigma
    0.25
    EFR
    0.25
     ventil
    0.24
     emotional
    0.24
     vent
    0.23
    	RTLR
    0.23
    å¿ĥçIJĨ
    0.23
     empathy
    0.23
    Activations Density 0.173%

    No Known Activations