© 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. 13843
    Prev
    Next
    INDEX
    Explanations

    railway station, office, port

    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
    rog
    -0.23
     Insider
    -0.21
    ->__
    -0.20
    æŃ£æĸĩ
    -0.19
    agr
    -0.19
    模
    -0.18
    讨
    -0.18
    åįļ主
    -0.18
    uid
    -0.18
     scope
    -0.18
    POSITIVE LOGITS
    交éĢļæŀ¢çº½
    0.30
    ç«ĻçĤ¹
    0.29
    æŀ¢çº½
    0.28
    ç»ĪçĤ¹
    0.27
    éĻĦè¿ijçļĦ
    0.26
    è¿Ľåĩºåı£
    0.25
    åĩºåħ¥å¢ĥ
    0.24
    大éŨ
    0.24
    éĿłè¿ij
    0.24
    åħ¥åı£
    0.24
    Activations Density 0.271%

    No Known Activations