© 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. 16456
    Prev
    Next
    INDEX
    Explanations

    diseases and production tasks

    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
     tran
    -0.20
    illo
    -0.20
    ä¸Ģå®ļ
    -0.20
    Smarty
    -0.19
    cir
    -0.19
    åĬŁ
    -0.19
    åĮ¹
    -0.19
     Irish
    -0.18
    èĬĤèĥ½
    -0.18
    uten
    -0.18
    POSITIVE LOGITS
    éĢł
    0.22
    /configuration
    0.19
    æ¼Ĥæµģ
    0.19
    åĨ·æ°´
    0.19
    éªĬ
    0.19
    _operations
    0.19
    Apart
    0.19
     fian
    0.18
     splitted
    0.18
    ç½ħ
    0.18
    Activations Density 8.603%

    No Known Activations