© 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. 14380
    Prev
    Next
    INDEX
    Explanations

    without notice or restriction

    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
    KIT
    -0.25
     EIF
    -0.21
    ä»Ĺ
    -0.20
    æ¥Ķ
    -0.20
     pale
    -0.20
    ences
    -0.19
    çľĭçľĭ
    -0.19
     ded
    -0.19
    éĩĮéĿ¢æľī
    -0.19
    cope
    -0.18
    POSITIVE LOGITS
    ç»ĻæĤ¨
    0.21
    å¯Łè§ī
    0.19
    ToFile
    0.19
    èĢ»
    0.19
    çļĦåıĺåĮĸ
    0.19
    DidChange
    0.18
    客æĪ·æľįåĬ¡
    0.18
    æģķ
    0.18
     slightest
    0.18
     ÐĴам
    0.17
    Activations Density 0.001%

    No Known Activations