© 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. 11941
    Prev
    Next
    INDEX
    Explanations

    event attendance

    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
    éĩįå¡ij
    -0.22
    æĵħéķ¿
    -0.22
    åįı
    -0.19
    ç»ıè¿ĩå¤ļå¹´
    -0.19
    ä¸İä¼Ĺ
    -0.19
    oste
    -0.19
    елÑĮ
    -0.19
    å¡ijéĢł
    -0.18
    _red
    -0.18
    é©°
    -0.18
    POSITIVE LOGITS
    人æķ°
    0.31
    人æ°Ķ
    0.29
    人次
    0.29
    人æµģ
    0.28
    åľºéĿ¢
    0.27
    æµģéĩı
    0.26
    人åı£
    0.26
    population
    0.25
    客æµģ
    0.23
    åİŁåĽłä¹ĭä¸Ģ
    0.23
    Activations Density 0.062%

    No Known Activations