© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12361
    Prev
    Next
    INDEX
    Explanations

    game names ending in .exe or -like

    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
    acen
    -0.22
    adro
    -0.20
    ök
    -0.20
    éĵ§
    -0.19
    æŃ¦ä¾ł
    -0.19
    礼æĭľ
    -0.19
    yaw
    -0.19
    lassen
    -0.19
    ç¿
    -0.18
    ToInt
    -0.18
    POSITIVE LOGITS
    -like
    0.26
    .exe
    0.24
     classic
    0.23
    -esque
    0.23
    çĬ¶
    0.21
    ä¼¼çļĦ
    0.21
     game
    0.21
    è¿Ļ款游æĪı
    0.21
    游æĪıä¸Ń
    0.21
    è¿Ļ款
    0.20
    Activations Density 0.036%

    No Known Activations