© 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. 16911
    Prev
    Next
    INDEX
    Explanations

    least number of dead

    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
    è¿ĻåĿĹ
    -0.21
    slaught
    -0.20
    常常
    -0.18
    为主
    -0.18
    dre
    -0.18
    UST
    -0.18
    itest
    -0.18
    对æīĭ
    -0.18
    uster
    -0.18
    ãģ«åŁº
    -0.18
    POSITIVE LOGITS
    伤亡
    0.26
    两åIJį
    0.24
    责任人
    0.23
    人æŃ»äº¡
    0.23
    个å¤ļ
    0.23
    迹象
    0.22
    éĢļæĬ¥
    0.22
    人æķ°
    0.21
    çĸijä¼¼
    0.21
    人åijĺ
    0.21
    Activations Density 0.040%

    No Known Activations