© 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. 11991
    Prev
    Next
    INDEX
    Explanations

    exercises, activities, tests, tasks, workshops, challenges

    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
    天涯
    -0.21
    åĬ¨åijĺ
    -0.20
    æ¹
    -0.20
    newline
    -0.20
     vibes
    -0.19
    æĹłç§ģ
    -0.19
    _extend
    -0.19
    åķ¡
    -0.19
    /state
    -0.19
    ãĤ¬ãĤ¤ãĥī
    -0.19
    POSITIVE LOGITS
    çݯèĬĤ
    0.28
    诸å¦Ĥ
    0.24
     tasks
    0.23
    ä»»åĬ¡
    0.23
    æĸ°é¢ĸ
    0.22
    centration
    0.21
    æľī趣
    0.21
    åĬ¨ä½ľ
    0.20
    éģĵåħ·
    0.20
    饮
    0.20
    Activations Density 0.026%

    No Known Activations