© 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. 14916
    Prev
    Next
    INDEX
    Explanations

    organizational and institutional titles

    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
    ä¼Ļ
    -0.19
    æĪ´çĿĢ
    -0.19
    ÑĨеп
    -0.18
    å¾Ĺ罪
    -0.18
    滨海
    -0.18
    indr
    -0.18
    åĽ¢ä¼Ļ
    -0.18
    ãĦŁ
    -0.18
    æĪ¢
    -0.18
    æī«é»ij
    -0.18
    POSITIVE LOGITS
     GSL
    0.20
    åĵº
    0.19
     Elder
    0.18
    ESA
    0.18
    窦
    0.18
    edian
    0.18
    åľ¨å¤ĸ
    0.18
     (::
    0.18
    å¿Ļç¢Į
    0.18
    thest
    0.18
    Activations Density 0.348%

    No Known Activations