© 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. 12889
    Prev
    Next
    INDEX
    Explanations

    widget, screen, desktop, hub, list, face, twin, Intent

    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
    èĤł
    -0.21
    æ·¼
    -0.20
    澡
    -0.19
    è¹Ĥ
    -0.19
    åį´è¢«
    -0.18
    æĭ¼æIJı
    -0.18
    è¡©
    -0.18
    ä¸¤åľ°
    -0.18
    粪
    -0.17
     Rodrig
    -0.17
    POSITIVE LOGITS
    åIJĦ家
    0.21
    èĸľ
    0.20
    åĬŁèĥ½
    0.20
    Android
    0.20
     Android
    0.19
    åľľ
    0.19
    åĢ¾æĸľ
    0.19
    -third
    0.19
    çķĮéĿ¢
    0.19
    建设çĶ¨åľ°
    0.19
    Activations Density 0.027%

    No Known Activations