© 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. 13640
    Prev
    Next
    INDEX
    Explanations

    a great deal of

    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
    巨头
    -0.18
    apos
    -0.17
    ä¸ĩä¸Ģ
    -0.17
     же
    -0.17
    idd
    -0.17
     аналог
    -0.17
    汶å·Ŀ
    -0.17
    ÑģÑĤи
    -0.17
    ções
    -0.16
    å¾Ĺ好
    -0.16
    POSITIVE LOGITS
    ма
    0.18
    å¬
    0.17
    format
    0.17
    onna
    0.17
    -needed
    0.17
    vant
    0.16
    议论
    0.15
     fuss
    0.15
    phis
    0.15
    że
    0.15
    Activations Density 0.019%

    No Known Activations