© 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. 12659
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    eway
    -0.20
    eco
    -0.20
    ç»ıæµİæĬĢæľ¯
    -0.19
    å¹³åĿĩæ°´å¹³
    -0.19
    çĸ¼çĹĽ
    -0.18
    anked
    -0.18
    æ·±åĪ»
    -0.18
    acco
    -0.18
    ooter
    -0.17
     Ðijа
    -0.17
    POSITIVE LOGITS
    ä»ĺè´¹
    0.21
     أج
    0.20
    iran
    0.20
    伶
    0.19
     odp
    0.18
    rib
    0.18
    å¢ĥ
    0.18
    ä¸į太
    0.18
    å¾Ĺä½ı
    0.18
    ABI
    0.18
    Activations Density 0.000%

    No Known Activations