© 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. 16362
    Prev
    Next
    INDEX
    Explanations

    best known for

    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
    ëĤľ
    -0.21
    èĢĨ
    -0.20
    VRT
    -0.18
    大åıij
    -0.18
    cope
    -0.18
    иÑĤеÑģÑĮ
    -0.18
     intention
    -0.18
    çĮ´
    -0.17
    ä¸Ģ缴éĥ½
    -0.17
     обÑĢаÑīа
    -0.17
    POSITIVE LOGITS
    arkan
    0.23
    ä½ľåĵģ
    0.22
    两项
    0.21
    çļĦåį°è±¡
    0.19
    pter
    0.19
    çªģåĩº
    0.19
    çļĦä½ľåĵģ
    0.18
    æĹ¥å¸¸å·¥ä½ľ
    0.18
    ä¸Ģåı¥è¯Ŀ
    0.18
    anness
    0.18
    Activations Density 0.065%

    No Known Activations