© 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. 13527
    Prev
    Next
    INDEX
    Explanations

    cross-country, cross-field, cross-frequency

    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
    outcome
    -0.21
    sville
    -0.20
    tails
    -0.18
    èIJ½ä¸ĭ
    -0.18
    (rv
    -0.17
    å¼¼
    -0.17
    æĹłç¼ĺ
    -0.17
     Outcome
    -0.17
    Outcome
    -0.17
    è§IJ
    -0.17
    POSITIVE LOGITS
     across
    0.33
    è·¨
    0.28
    æĢ§å¼º
    0.23
    å¾ĢæĿ¥
    0.23
     междÑĥ
    0.23
    å¹¿æ³Ľ
    0.23
     between
    0.22
    ä¸įåIJĮ
    0.22
    è£Ĩ
    0.22
     Across
    0.21
    Activations Density 0.105%

    No Known Activations