© 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. 14340
    Prev
    Next
    INDEX
    Explanations

    simulating or practicing scenarios

    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
    -lined
    -0.21
    xeb
    -0.19
    æ®ĥ
    -0.19
    æĹ¥äº§
    -0.19
     sı
    -0.18
    dle
    -0.18
    å·²ç»ıæĺ¯
    -0.18
    ialis
    -0.18
    éļ¶å±ŀäºİ
    -0.18
    以èī²
    -0.18
    POSITIVE LOGITS
    æ¼Ķç»ĥ
    0.29
    模æĭŁ
    0.27
     simulation
    0.26
    æ¼Ķä¹ł
    0.26
    simulation
    0.25
    ä»¿çľŁ
    0.25
    simulate
    0.24
    æ¼Ķ
    0.23
    (dummy
    0.23
    Simulation
    0.21
    Activations Density 0.055%

    No Known Activations