© 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. 12115
    Prev
    Next
    INDEX
    Explanations

    railway station

    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
    èĢĺ
    -0.24
    æīĽ
    -0.20
    çĢļ
    -0.20
    éħ©
    -0.19
    çĶŁäº§çº¿
    -0.19
    åIJĦçľģ
    -0.18
    汩
    -0.18
    çĶŁæ´»åľ¨
    -0.18
    渤
    -0.18
    лив
    -0.18
    POSITIVE LOGITS
    交éĢļæŀ¢çº½
    0.23
    车ç«Ļ
    0.23
    ä¸ĭ车
    0.23
     terminal
    0.22
    ç«Ļ
    0.22
    ç«ĻçĤ¹
    0.21
    Terminal
    0.21
    æŃ¥è¡Į
    0.20
    terminal
    0.20
    åĿĢ
    0.20
    Activations Density 0.044%

    No Known Activations