© 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. 12134
    Prev
    Next
    INDEX
    Explanations

    since then

    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
     eventually
    -0.24
     eventual
    -0.23
     Eventually
    -0.21
    èĢĨ
    -0.20
    ä½ľçĶ¨
    -0.20
    ãĤ¬ãĤ¤
    -0.19
    çľĭçľĭ
    -0.18
    æĬ¬
    -0.17
    éĥĩ
    -0.17
     dest
    -0.17
    POSITIVE LOGITS
    以æĿ¥
    0.40
    以ä¾Ĩ
    0.39
    æĪIJç«ĭ以æĿ¥
    0.39
    年以æĿ¥
    0.35
    æľĪ以æĿ¥
    0.32
     inception
    0.29
    ãģļãģ£ãģ¨
    0.27
    since
    0.25
     since
    0.24
    ä¸Ģ缴éĥ½
    0.23
    Activations Density 0.076%

    No Known Activations