© 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. 13766
    Prev
    Next
    INDEX
    Explanations

    bill

    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
    /gin
    -0.19
     kå
    -0.19
    eur
    -0.18
    è¿Ļ个游æĪı
    -0.18
    对åħ¶çľŁå®ŀ
    -0.18
    å¥
    -0.17
    éĹ®é¢ĺæĺ¯
    -0.17
    æĪijçļĦå¿ĥ
    -0.17
    /goto
    -0.17
    ä¸įä¹ı
    -0.17
    POSITIVE LOGITS
     ÐIJлекÑģан
    0.20
    ä¸Ń
    0.20
    åľ¨åħ¨åĽ½
    0.19
    åľ¨å¤ĸ
    0.19
    ERA
    0.18
    ILES
    0.17
    ANGES
    0.17
    åĨħ容
    0.17
     Sinn
    0.17
    çļĦ主è¦ģ
    0.17
    Activations Density 0.017%

    No Known Activations