© 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. 14112
    Prev
    Next
    INDEX
    Explanations

    first

    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
    éļıæŶ
    -0.20
    èĩªä»İ
    -0.19
    åĪļ好
    -0.19
    åıªè¦ģ
    -0.18
    uario
    -0.18
    å¥ijæľº
    -0.17
    çľĭå¾Ĺ
    -0.17
     suá»ijt
    -0.17
    çĵ¶
    -0.17
    æľīæŶåĢĻ
    -0.17
    POSITIVE LOGITS
    åħĪ
    0.25
    åIJĥ饱
    0.20
    è¢Ĥ
    0.19
    à¹Īà¸Ńà¸Ļ
    0.19
    ç¡®ä¿Ŀ
    0.19
     acquaintance
    0.18
    äºĨ解ä¸Ģä¸ĭ
    0.18
    (before
    0.18
    交ç»Ļ
    0.18
    第ä¸ĢæŃ¥
    0.18
    Activations Density 0.047%

    No Known Activations