© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14974
    Prev
    Next
    INDEX
    Explanations

    exit, remove, close

    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
    æĺİçŁ¥
    -0.20
    äºī
    -0.19
     borderBottom
    -0.19
    ç¦ģåĮº
    -0.18
    eted
    -0.18
    ä¸įåIJĥ
    -0.18
    éļĻ
    -0.18
    ä¸IJ
    -0.17
    ODB
    -0.17
    -Requested
    -0.17
    POSITIVE LOGITS
    itr
    0.19
     khá»ıi
    0.18
    éļħ
    0.17
    Zip
    0.17
     Andersen
    0.17
     AMA
    0.17
    ä¸Ģä¸ĭåŃIJå°±
    0.17
    DevExpress
    0.17
     ZIP
    0.17
     Plum
    0.17
    Activations Density 0.001%

    No Known Activations