© 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. 16778
    Prev
    Next
    INDEX
    Explanations

    footwear, anatomy, Q&A

    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
    æijĩ头
    -0.21
    ovy
    -0.20
    icer
    -0.19
    tower
    -0.19
    ç¢į
    -0.19
    -router
    -0.19
    æ¸ĹéĢı
    -0.18
     plasma
    -0.18
    é»ı
    -0.18
    ç²ĺ
    -0.17
    POSITIVE LOGITS
    åľĥ
    0.20
     Aub
    0.20
    PDO
    0.19
    å¥ģ
    0.19
    éĿ¢åĮħ
    0.18
    ä½ĵè´´
    0.18
    ç¡ļ
    0.18
    庳
    0.18
    å·§
    0.17
     hottest
    0.17
    Activations Density 0.015%

    No Known Activations