© 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. 16412
    Prev
    Next
    INDEX
    Explanations

    groups within a community or organization

    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
    亿ä¸ĩ
    -0.21
    人们
    -0.21
    ä¸ĸ人
    -0.20
    è¿ĻåIJį
    -0.19
    人åĢij
    -0.19
    ä¸į失
    -0.19
    人们çļĦ
    -0.19
    éĽĩ主
    -0.19
    让人们
    -0.19
    好äºĭ
    -0.19
    POSITIVE LOGITS
     vụ
    0.21
    ä¹ĭéĹ´çļĦ
    0.19
    èł²
    0.18
    è°ª
    0.18
    åħ±åIJĮåĬªåĬĽ
    0.18
    åįłæ¯Ķ
    0.17
    ä¹ĭéĹ´
    0.17
     tow
    0.17
    éĢĹ
    0.17
    è¿ŁåĪ°
    0.17
    Activations Density 0.071%

    No Known Activations