© 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. 12025
    Prev
    Next
    INDEX
    Explanations

    mathematics and calculations

    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
    ä¿Ŀ驾æĬ¤
    -0.22
    åıĸå¾Ĺ以åıĬ
    -0.20
    åĪ©çĶ¨æĤ¨çļĦ
    -0.20
    _FMT
    -0.19
    onica
    -0.19
    éĵ
    -0.19
    æĪĸå¤ļæĪĸ
    -0.19
     enlight
    -0.18
    å¸Ńæī§è¡Į
    -0.18
    æĪĸå¤ļæĪĸå°ij
    -0.18
    POSITIVE LOGITS
    æĭĴç»Ŀ
    0.21
    å§ĭç»ĪåĿļæĮģ
    0.21
    åĽº
    0.21
    æĭĴ
    0.20
    åĽ¢
    0.20
    èĩªæ²»
    0.19
    æĥħ绪
    0.19
    åīįçŀ»
    0.19
    å¿ĥå¢ĥ
    0.19
    ære
    0.19
    Activations Density 0.193%

    No Known Activations