© 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. 13195
    Prev
    Next
    INDEX
    Explanations

    dementia, AR, Hardware, multinomial

    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¤ĸæı´
    -0.20
    æĹłè®ºå¦Ĥä½ķ
    -0.20
    æģ¢
    -0.20
    èĬŃ
    -0.19
    ä½ĵåĪ¶
    -0.19
    åľ¨åIJĮä¸Ģ
    -0.18
    xhr
    -0.18
    èIJ½åħ¥
    -0.18
    /high
    -0.18
    ä¸Ģèĩ´
    -0.18
    POSITIVE LOGITS
    ä¸įåĥı
    0.54
    ä¸įåIJĮäºİ
    0.46
    èĢĮéĿŀ
    0.43
    èĢĮä¸įæĺ¯
    0.43
     unlike
    0.42
     rather
    0.40
    Unlike
    0.40
    rather
    0.38
     Unlike
    0.37
    ä»£æĽ¿
    0.37
    Activations Density 1.322%

    No Known Activations