© 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. 15600
    Prev
    Next
    INDEX
    Explanations

    Adriatic, endothelin, endothelial

    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
    /feed
    -0.23
    aran
    -0.19
    å®īç½®
    -0.19
    onymous
    -0.19
    pon
    -0.18
     pon
    -0.18
    åľ¨æ·±åľ³
    -0.17
    æĪIJæŀľè½¬åĮĸ
    -0.17
     Vere
    -0.17
     head
    -0.17
    POSITIVE LOGITS
    enos
    0.21
    æµ·å²Ľ
    0.19
     wes
    0.18
    åĿĮ
    0.18
    诸
    0.18
    è¯Ń
    0.18
     plates
    0.18
    exo
    0.18
    ä¼łéĢģ
    0.17
    cott
    0.17
    Activations Density 0.017%

    No Known Activations