© 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. 10717
    Prev
    Next
    INDEX
    Explanations

    futon-a-thon

    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
    #End
    -0.21
    ç»İ
    -0.20
     Estate
    -0.17
    vos
    -0.17
     Abram
    -0.17
    ND
    -0.17
    çļĦéĤ£ä¸ª
    -0.17
     вÑĭбÑĢ
    -0.17
    lers
    -0.17
    èŀ
    -0.17
    POSITIVE LOGITS
    åIJĬ
    0.20
    å¥łåŁº
    0.19
    åŃ£
    0.19
    æĪij以为
    0.19
    otto
    0.18
    actics
    0.18
     season
    0.18
    TP
    0.18
     mann
    0.18
     quat
    0.18
    Activations Density 0.348%

    No Known Activations