© 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. 11822
    Prev
    Next
    INDEX
    Explanations

    green bean, tea, color

    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
     bid
    -0.24
    æ³īæ°´
    -0.21
    bid
    -0.19
    teenth
    -0.18
     idi
    -0.18
    ogle
    -0.18
    Gravity
    -0.17
    ollen
    -0.17
    å£ij
    -0.17
    å®Įç¾İçļĦ
    -0.17
    POSITIVE LOGITS
    æ£Ģå¯Ł
    0.23
    ãģ¾ãģ¾
    0.20
    noinspection
    0.19
    æĶ¶ç´§
    0.19
    å¤ı
    0.18
    raw
    0.18
    æĸĩç«łæĿ¥æºIJ
    0.18
    stem
    0.18
    æľīæŶåĢĻ
    0.17
    leur
    0.17
    Activations Density 0.004%

    No Known Activations