© 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. 16572
    Prev
    Next
    INDEX
    Explanations

    modified, annotated, stabilized, equipped

    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
    WF
    -0.23
    大èĩªçĦ¶
    -0.20
    æİĸ
    -0.19
    ↵↵
    -0.19
    Constants
    -0.18
    åĴĮå®ĮåĸĦ
    -0.18
    orts
    -0.17
     scal
    -0.17
    Compet
    -0.17
    ĸ
    -0.17
    POSITIVE LOGITS
    ä¸ĭçļĦ
    0.31
    è¿ĩçļĦ
    0.27
    åľ¨åĨħçļĦ
    0.22
    çļĦå°ı
    0.22
    çļĦä¸ľè¥¿
    0.21
    çļĦæľįåĬ¡
    0.20
    çļĦé£Łçī©
    0.20
    åľºåIJĪ
    0.20
    åŀĭ
    0.20
    çļĦèµĦéĩij
    0.20
    Activations Density 0.312%

    No Known Activations