© 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. 11755
    Prev
    Next
    INDEX
    Explanations

    parts of papers or series

    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
    .PNG
    -0.22
    åŀĽ
    -0.21
     Anita
    -0.20
    nest
    -0.19
    çļĦä¸Ģç§į
    -0.19
    rac
    -0.18
    çļĦä¸Ģ款
    -0.18
    è¾Ļ
    -0.17
    .png
    -0.17
     wash
    -0.17
    POSITIVE LOGITS
     part
    0.27
    ç³»åĪĹ
    0.26
    çºĮ
    0.26
     ÑĩаÑģÑĤÑĮ
    0.25
    éĥ¨åĪĨ
    0.25
    ç»Ń
    0.25
     Part
    0.25
    ä¸ĢæľŁ
    0.23
     اÙĦجز
    0.23
     series
    0.22
    Activations Density 0.200%

    No Known Activations