© 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. 11701
    Prev
    Next
    INDEX
    Explanations

    late [NAME/TITLE/EVENT]

    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
    ç½ijç»ľä¼łæĴŃ
    -0.20
    èĻIJ
    -0.19
    æݥ触
    -0.19
    éĺµå®¹
    -0.19
    éĹº
    -0.18
    çºłéĶĻ
    -0.18
    è¿ĻäºĽäºº
    -0.18
    æ£Ģ
    -0.18
    è¿Ļåıªæĺ¯
    -0.18
    Pocket
    -0.18
    POSITIVE LOGITS
    ongs
    0.21
     Chambers
    0.20
    ä¸ī代
    0.19
    .setHeight
    0.19
    ŀæĢ§
    0.18
    æĮļ
    0.18
    agogue
    0.18
     Conj
    0.18
    omo
    0.18
    =DB
    0.18
    Activations Density 0.004%

    No Known Activations