© 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. 11246
    Prev
    Next
    INDEX
    Explanations

    Cay, virus, python

    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
     Caf
    -0.20
    èĮ´
    -0.19
    dings
    -0.19
    /language
    -0.18
    沪
    -0.17
    æ¥Ń
    -0.17
    ä¸įéĶĪ
    -0.17
    ãģ¬
    -0.17
    /wait
    -0.16
    æľīéĴĪ对æĢ§
    -0.16
    POSITIVE LOGITS
    iest
    0.18
    ments
    0.18
    es
    0.18
    æ¡ģ
    0.18
    tures
    0.18
    metics
    0.18
    ermo
    0.18
    thon
    0.18
    ieres
    0.18
    mouth
    0.18
    Activations Density 0.003%

    No Known Activations