© 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. 13815
    Prev
    Next
    INDEX
    Explanations

    suffix "-lated" or "-ation"

    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
    缣
    -0.19
    åĪĨæľŁ
    -0.19
    é¼IJ
    -0.19
    æĹłç¼ĺ
    -0.19
    åij¨æģ©
    -0.19
     пÑĢеимÑĥÑīеÑģÑĤв
    -0.18
    峦
    -0.18
    emark
    -0.18
    reet
    -0.18
    inders
    -0.18
    POSITIVE LOGITS
    è¿ĺæĥ³
    0.22
    è¦ģçĶ¨
    0.21
    antes
    0.21
    æ¯ıä½į
    0.20
     individual
    0.20
    æķ´ä¸ª
    0.20
    à¹īา
    0.20
    ãģıãĤĭ
    0.19
    ä½ľåĵģåĨħ容
    0.19
    人å¿ĥ
    0.19
    Activations Density 0.020%

    No Known Activations