© 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. 16188
    Prev
    Next
    INDEX
    Explanations

    adjectives describing states or actions

    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
    帷
    -0.19
    é¼Ļ
    -0.19
    å¸ı
    -0.19
    ddy
    -0.18
    è¿Ļä¸Ģ天
    -0.18
    è¿ĩå¹´
    -0.18
    磮
    -0.18
    à¸Ĥาà¸Ķ
    -0.18
    èĢĮä¸Ķ
    -0.18
    gne
    -0.17
    POSITIVE LOGITS
    åį´
    0.28
     simultaneously
    0.28
    åIJİèĢħ
    0.26
    åį´æĺ¯
    0.26
    缸ç»ĵåIJĪ
    0.26
     alike
    0.26
    åį´åıĪ
    0.25
    两èĢħ
    0.24
     latter
    0.24
     equally
    0.24
    Activations Density 0.225%

    No Known Activations