© 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. 16938
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
    buff
    -0.21
    EEEE
    -0.20
    VICE
    -0.19
    éļħ
    -0.18
    texts
    -0.18
    èĢĮå·²
    -0.18
    ighton
    -0.18
    ubbo
    -0.18
    大èĥĨ
    -0.18
    FIELDS
    -0.17
    POSITIVE LOGITS
    æĮģæľī人
    0.19
    èĢķèĢĺ
    0.19
    çݯå¢ĥä¿ĿæĬ¤
    0.18
    èįĦ
    0.18
    å»ºè®¾é¡¹çĽ®
    0.18
    ä¿Ŀåģ¥
    0.18
     ниже
    0.17
    âĸ¸
    0.17
    æĩĴå¾Ĺ
    0.17
    建设工ç¨ĭ
    0.17
    Activations Density 0.035%

    No Known Activations