© 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. 16879
    Prev
    Next
    INDEX
    Explanations

    license identifier

    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
    åĤ¾
    -0.18
    å¦
    -0.18
    _Core
    -0.18
     midd
    -0.18
    reflection
    -0.17
    PropertyValue
    -0.17
    ä¸ŃéĢĶ
    -0.17
     лиÑĤеÑĢ
    -0.17
    -br
    -0.17
     Pey
    -0.16
    POSITIVE LOGITS
    éŨæĪ·ç½ijç«Ļ
    0.20
    è¿Ļåıª
    0.20
    Cog
    0.20
    å¹¼ç¨ļ
    0.19
    èıĢ
    0.19
    è¿Ļæĺ¯ä¸Ģç§į
    0.18
    ABCDEFG
    0.18
    稿
    0.17
    minster
    0.17
     ticker
    0.17
    Activations Density 0.007%

    No Known Activations