© 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. 16894
    Prev
    Next
    INDEX
    Explanations

    news organizations and locations

    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
    å¨ĥå¨ĥ
    -0.26
     harvest
    -0.21
    ä¸Ĭæ¦ľ
    -0.21
    èħ°
    -0.20
    æĥ¶
    -0.20
    éģij
    -0.20
    äºĮ代
    -0.20
     yên
    -0.19
    ä¸Ĭå¸Ĥ
    -0.19
    åľ¨æĦı
    -0.19
    POSITIVE LOGITS
    ä¸Ģ个æľĪ
    0.19
    lopedia
    0.18
     Dealer
    0.18
    ndx
    0.18
    lore
    0.18
    erville
    0.17
    Mel
    0.17
    åIJĪåĬĽ
    0.17
     Jed
    0.17
    èIJĮ
    0.17
    Activations Density 0.010%

    No Known Activations