© 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. 16415
    Prev
    Next
    INDEX
    Explanations

    antivirus and adblocker software

    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
    æĮ¯å¥ĭ
    -0.21
     Telegram
    -0.21
     telegram
    -0.20
    éĢı
    -0.19
    åłĤ
    -0.19
    /API
    -0.19
    avier
    -0.19
    å¿ĥæĦı
    -0.18
     Siri
    -0.18
    egra
    -0.18
    POSITIVE LOGITS
    noinspection
    0.24
    æ¸ħéĻ¤
    0.23
     purchased
    0.21
    æİĴæŁ¥
    0.20
    Installed
    0.20
    软件
    0.20
    esp
    0.20
    éĺ²å¾¡
    0.20
    recommended
    0.20
    æĪIJé¾Ļ
    0.20
    Activations Density 0.020%

    No Known Activations