© 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. 11741
    Prev
    Next
    INDEX
    Explanations

    ballet dancers and choreographers

    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
    åľ¨çݩ家ä¸Ń
    -0.26
    Speaker
    -0.22
     treason
    -0.20
    åĸĩåıŃ
    -0.20
    инÑĦ
    -0.20
    çħ®
    -0.19
    ombo
    -0.19
    getc
    -0.19
    游æĪıåī¯æľ¬
    -0.19
    åı£æľį
    -0.19
    POSITIVE LOGITS
    èĪŀè¹Ī
    0.39
    åĬ¨ä½ľ
    0.36
     dancer
    0.36
     dancers
    0.35
    èĪŀ
    0.32
    表æ¼Ķ
    0.32
    åĭķä½ľ
    0.31
    æ¼Ķç»İ
    0.30
     ballet
    0.29
     chore
    0.28
    Activations Density 0.040%

    No Known Activations