© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12584
    Prev
    Next
    INDEX
    Explanations

    one followed by another

    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
     other
    -0.20
    åIJĮäºĭ
    -0.19
    hood
    -0.18
     ÑĦинанÑģов
    -0.18
    ingleton
    -0.18
    ãĤĤãģ£ãģ¨
    -0.18
    vertiser
    -0.18
    uzzi
    -0.18
    alking
    -0.17
    _checkout
    -0.17
    POSITIVE LOGITS
    缸èģļ
    0.21
    综åIJĪæĢ§
    0.21
    Magnitude
    0.21
    æIJĢ
    0.19
    姻
    0.19
    ä¸ĢåĽŀäºĭ
    0.18
    巨大
    0.18
    æ±ł
    0.18
    åľ¨ä¸Ģèµ·
    0.18
    âĺĿ
    0.18
    Activations Density 0.031%

    No Known Activations