© 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. 16638
    Prev
    Next
    INDEX
    Explanations

    leading

    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
    -trigger
    -0.20
    åĩºçĤī
    -0.19
    PID
    -0.18
     seams
    -0.18
    -article
    -0.18
    æį¢å±Ĭ
    -0.18
    é¦ĸå¯Į
    -0.18
    emoji
    -0.18
     Pfizer
    -0.18
    ä»ĬåĽŀãģ¯
    -0.17
    POSITIVE LOGITS
    éĿ¢åIJij
    0.24
    综åIJĪæĢ§
    0.24
    èĢģçīĮ
    0.22
    åħ¨æĹ¥
    0.21
    ä¸Ģ个å¤ļ
    0.21
    åħ¨åĽ½
    0.21
    æ§IJ
    0.20
     Affero
    0.20
    综åIJĪ
    0.20
    èĩªåĬ©
    0.20
    Activations Density 0.045%

    No Known Activations