© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12344
    Prev
    Next
    INDEX
    Explanations

    HTML `<body>` tag

    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
    帮åĬ©ä¼ģä¸ļ
    -0.25
    èĩ´åij½
    -0.20
    åĪ¶æŃ¢
    -0.20
    çģĮ
    -0.20
    èĸĦå¼±
    -0.19
     OEM
    -0.19
    ç¿»å¼Ģ
    -0.18
    ighting
    -0.18
    DECL
    -0.18
    åij¨è¾¹
    -0.18
    POSITIVE LOGITS
     bullets
    0.20
    ello
    0.20
     Clem
    0.19
    åĮºåĿĹéĵ¾
    0.18
     ì²ĺ
    0.18
     bullet
    0.18
    expert
    0.17
    æľ¬ç½ijç«Ļ
    0.17
    THREAD
    0.17
    æĮ¤
    0.17
    Activations Density 0.003%

    No Known Activations