© 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. 11578
    Prev
    Next
    INDEX
    Explanations

    lists and examples

    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
    梳
    -0.22
    ä¸ī级
    -0.21
    åĽĽçº§
    -0.20
    åij¼åĴĮ
    -0.20
    åĴĮåıijå±ķ
    -0.20
    isNew
    -0.19
    rlen
    -0.18
     cú
    -0.18
    ungan
    -0.18
    _TYPEDEF
    -0.17
    POSITIVE LOGITS
     Moy
    0.21
    æĢ»ä¹ĭ
    0.21
    ä¸ĢäºĽ
    0.20
    лÑĮ
    0.19
     stripped
    0.19
    /etc
    0.18
     fold
    0.18
     gent
    0.18
    ä¸įå°ij
    0.18
    (*)
    0.18
    Activations Density 0.070%

    No Known Activations